Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4555 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1138. Min Range: -6.1138
Max Act: 6.1138. Min Act: -0.1700
Data Index: 1565745 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1138. Min Range: -6.1138
Max Act: 6.0826. Min Act: -0.1700
Data Index: 4484629 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1138. Min Range: -6.1138
Max Act: 6.1138. Min Act: -0.1700
Data Index: 2617366 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1138. Min Range: -6.1138
Max Act: 6.0201. Min Act: -0.1700
Data Index: 8473960 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1138. Min Range: -6.1138
Max Act: 6.0513. Min Act: -0.1700
Data Index: 1505347 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1138. Min Range: -6.1138
Max Act: 6.0201. Min Act: -0.1700
Data Index: 1080692 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1138. Min Range: -6.1138
Max Act: 6.0201. Min Act: -0.1700
Data Index: 2366814 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.9263. Min Act: -0.1700
Data Index: 4587573 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.9263. Min Act: -0.1700
Data Index: 2962873 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.9263. Min Act: -0.1700
Data Index: 3761119 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8638. Min Act: -0.1700
Data Index: 1926529 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8638. Min Act: -0.1700
Data Index: 5841953 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8326. Min Act: -0.1700
Data Index: 4166438 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8326. Min Act: -0.1700
Data Index: 7944584 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8326. Min Act: -0.1700
Data Index: 3156698 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8326. Min Act: -0.1700
Data Index: 6113641 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.7701. Min Act: -0.1700
Data Index: 6643478 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8013. Min Act: -0.1700
Data Index: 7910502 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8013. Min Act: -0.1700
Data Index: 1700105 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1138. Min Range: -6.1138
Max Act: 5.8013. Min Act: -0.1700
Data Index: 825378 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19