Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.6409. Min Act: -0.1700
Data Index: 6183339 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.6096. Min Act: -0.1700
Data Index: 2189173 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.6096. Min Act: -0.1700
Data Index: 7973928 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.6096. Min Act: -0.1700
Data Index: 7885515 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.3284. Min Act: -0.1700
Data Index: 170697 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.2971. Min Act: -0.1700
Data Index: 2540181 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.3284. Min Act: -0.1700
Data Index: 8506337 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.2971. Min Act: -0.1700
Data Index: 5786157 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.2346. Min Act: -0.1700
Data Index: 7534307 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1721. Min Act: -0.1700
Data Index: 7282577 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1409. Min Act: -0.1700
Data Index: 5081758 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1409. Min Act: -0.1700
Data Index: 933802 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1409. Min Act: -0.1700
Data Index: 2239528 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1409. Min Act: -0.1700
Data Index: 3575708 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1096. Min Act: -0.1700
Data Index: 4261639 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1096. Min Act: -0.1700
Data Index: 7011256 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.1096. Min Act: -0.1700
Data Index: 3062638 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.0784. Min Act: -0.1700
Data Index: 3062642 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.0784. Min Act: -0.1700
Data Index: 529941 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6409. Min Range: -6.6409
Max Act: 6.0784. Min Act: -0.1700
Data Index: 1298728 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19