Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5045 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.4805. Min Act: -0.1700
Data Index: 7935025 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.4180. Min Act: -0.1700
Data Index: 1620934 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3243. Min Act: -0.1700
Data Index: 3451458 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 8657139 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 6054334 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2618. Min Act: -0.1700
Data Index: 4084801 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2305. Min Act: -0.1700
Data Index: 3745729 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2305. Min Act: -0.1700
Data Index: 3328327 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2618. Min Act: -0.1700
Data Index: 4550494 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2305. Min Act: -0.1700
Data Index: 3451459 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2618. Min Act: -0.1700
Data Index: 4550490 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 307034 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 1196143 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 7780409 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 6068406 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 8315416 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 3652491 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 675901 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 4301316 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1993. Min Act: -0.1700
Data Index: 7413146 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19