Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1007 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.5070. Min Act: -0.1700
Data Index: 7256579 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.2570. Min Act: -0.1700
Data Index: 637311 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1945. Min Act: -0.1700
Data Index: 5863158 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1945. Min Act: -0.1700
Data Index: 1765993 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1319. Min Act: -0.1700
Data Index: 3089359 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1319. Min Act: -0.1700
Data Index: 4529817 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1007. Min Act: -0.1700
Data Index: 2068523 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1319. Min Act: -0.1700
Data Index: 6036398 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0694. Min Act: -0.1700
Data Index: 3126017 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1007. Min Act: -0.1700
Data Index: 808359 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0694. Min Act: -0.1700
Data Index: 2920808 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0382. Min Act: -0.1700
Data Index: 4980130 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0694. Min Act: -0.1700
Data Index: 8818243 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.1007. Min Act: -0.1700
Data Index: 8470232 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0694. Min Act: -0.1700
Data Index: 2524980 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0694. Min Act: -0.1700
Data Index: 2214929 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0382. Min Act: -0.1700
Data Index: 6713477 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0382. Min Act: -0.1700
Data Index: 5610271 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0382. Min Act: -0.1700
Data Index: 1250081 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5070. Min Range: -4.5070
Max Act: 4.0069. Min Act: -0.1700
Data Index: 3866381 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19