Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 938 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.9427. Min Act: -0.1700
Data Index: 3035573 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.9427. Min Act: -0.1700
Data Index: 4680261 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8916. Min Act: -0.1700
Data Index: 3956828 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.9087. Min Act: -0.1700
Data Index: 8691823 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8746. Min Act: -0.1700
Data Index: 7351965 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8746. Min Act: -0.1700
Data Index: 2531097 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8574. Min Act: -0.1700
Data Index: 5780959 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8403. Min Act: -0.1700
Data Index: 3245197 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8574. Min Act: -0.1700
Data Index: 1448215 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8574. Min Act: -0.1700
Data Index: 500737 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8746. Min Act: -0.1700
Data Index: 3017818 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8232. Min Act: -0.1700
Data Index: 4262145 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8403. Min Act: -0.1700
Data Index: 8578648 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8403. Min Act: -0.1700
Data Index: 4536299 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8232. Min Act: -0.1700
Data Index: 3091994 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8403. Min Act: -0.1700
Data Index: 2133777 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8403. Min Act: -0.1700
Data Index: 1138881 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8403. Min Act: -0.1700
Data Index: 2381053 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8232. Min Act: -0.1700
Data Index: 164951 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9427. Min Range: -1.9427
Max Act: 1.8232. Min Act: -0.1700
Data Index: 5656047 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19