Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.1255. Min Act: -0.1700
Data Index: 6156804 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.0630. Min Act: -0.1700
Data Index: 6431045 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.0005. Min Act: -0.1700
Data Index: 5436887 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.0005. Min Act: -0.1700
Data Index: 5573775 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.0630. Min Act: -0.1700
Data Index: 4475793 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.0005. Min Act: -0.1700
Data Index: 6431048 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.0005. Min Act: -0.1700
Data Index: 4588340 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1255. Min Range: -8.1255
Max Act: 8.0005. Min Act: -0.1700
Data Index: 2330507 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.8130. Min Act: -0.1700
Data Index: 7524712 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.7817. Min Act: -0.1700
Data Index: 5660864 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.8755. Min Act: -0.1700
Data Index: 5157277 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.8755. Min Act: -0.1700
Data Index: 8438849 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.8130. Min Act: -0.1700
Data Index: 5434832 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.7817. Min Act: -0.1700
Data Index: 3208283 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.8130. Min Act: -0.1700
Data Index: 5745900 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.7505. Min Act: -0.1700
Data Index: 7168741 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.7505. Min Act: -0.1700
Data Index: 2814726 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.7817. Min Act: -0.1700
Data Index: 3421153 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.7192. Min Act: -0.1700
Data Index: 5043386 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1255. Min Range: -8.1255
Max Act: 7.7192. Min Act: -0.1700
Data Index: 3634350 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19