Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 18.5183. Min Range: -18.5183
Max Act: 18.5183. Min Act: -0.1700
Data Index: 3532161 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.5183. Min Range: -18.5183
Max Act: 18.3933. Min Act: -0.1700
Data Index: 2876297 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.5183. Min Range: -18.5183
Max Act: 18.5183. Min Act: -0.1700
Data Index: 4984217 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.5183. Min Range: -18.5183
Max Act: 18.1433. Min Act: -0.1700
Data Index: 58206 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.5183. Min Range: -18.5183
Max Act: 18.2683. Min Act: -0.1700
Data Index: 1296658 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.5183. Min Range: -18.5183
Max Act: 18.0183. Min Act: -0.1700
Data Index: 3415764 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.8933. Min Act: -0.1700
Data Index: 4034816 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.6433. Min Act: -0.1700
Data Index: 6394447 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.5183. Min Act: -0.1700
Data Index: 2243209 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.3933. Min Act: -0.1700
Data Index: 8322112 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.3933. Min Act: -0.1700
Data Index: 740519 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.3933. Min Act: -0.1700
Data Index: 5589962 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.3933. Min Act: -0.1700
Data Index: 7169856 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.3933. Min Act: -0.1700
Data Index: 8605777 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.1433. Min Act: -0.1700
Data Index: 5557207 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.0183. Min Act: -0.1700
Data Index: 5739118 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.1433. Min Act: -0.1700
Data Index: 5811709 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.1433. Min Act: -0.1700
Data Index: 2370385 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.5183. Min Range: -18.5183
Max Act: 17.0183. Min Act: -0.1700
Data Index: 5675441 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.5183. Min Range: -18.5183
Max Act: 16.8933. Min Act: -0.1700
Data Index: 6521438 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19