Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 388 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2454. Min Range: -8.2454
Max Act: 8.2454. Min Act: -0.1700
Data Index: 860309 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.9954. Min Act: -0.1700
Data Index: 1184480 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.8391. Min Act: -0.1700
Data Index: 6612109 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.7141. Min Act: -0.1700
Data Index: 8147665 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.6204. Min Act: -0.1700
Data Index: 3181717 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.5891. Min Act: -0.1700
Data Index: 691693 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4954. Min Act: -0.1700
Data Index: 6185287 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4954. Min Act: -0.1700
Data Index: 8255856 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.5266. Min Act: -0.1700
Data Index: 6612107 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4329. Min Act: -0.1700
Data Index: 6969371 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4016. Min Act: -0.1700
Data Index: 7751650 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4016. Min Act: -0.1700
Data Index: 5045844 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.3704. Min Act: -0.1700
Data Index: 2786728 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4016. Min Act: -0.1700
Data Index: 1920825 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4016. Min Act: -0.1700
Data Index: 8199748 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.3704. Min Act: -0.1700
Data Index: 4199338 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4016. Min Act: -0.1700
Data Index: 5386002 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4016. Min Act: -0.1700
Data Index: 2689390 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.3704. Min Act: -0.1700
Data Index: 3273232 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2454. Min Range: -8.2454
Max Act: 7.4016. Min Act: -0.1700
Data Index: 195010 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19