Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4467 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0451. Min Range: -7.0451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 6476142 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0451. Min Range: -7.0451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 8013087 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0451. Min Range: -7.0451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 1722114 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0451. Min Range: -7.0451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 8612231 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.9514. Min Act: -0.1700
Data Index: 5890570 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.8889. Min Act: -0.1700
Data Index: 7987739 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.7951. Min Act: -0.1700
Data Index: 6045235 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.7639. Min Act: -0.1700
Data Index: 2909085 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.7326. Min Act: -0.1700
Data Index: 6622854 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.7326. Min Act: -0.1700
Data Index: 3784874 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.7014. Min Act: -0.1700
Data Index: 3682712 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.6701. Min Act: -0.1700
Data Index: 305234 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.7014. Min Act: -0.1700
Data Index: 8420656 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.7014. Min Act: -0.1700
Data Index: 2200855 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.6389. Min Act: -0.1700
Data Index: 8051468 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.6701. Min Act: -0.1700
Data Index: 6954431 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.6701. Min Act: -0.1700
Data Index: 7379498 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.6701. Min Act: -0.1700
Data Index: 7382756 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.6389. Min Act: -0.1700
Data Index: 1303712 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0451. Min Range: -7.0451
Max Act: 6.6389. Min Act: -0.1700
Data Index: 5179204 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19