Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.3976. Min Act: -0.1700
Data Index: 2926742 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.3351. Min Act: -0.1700
Data Index: 2726248 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.3351. Min Act: -0.1700
Data Index: 1895475 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.3351. Min Act: -0.1700
Data Index: 6340489 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.2726. Min Act: -0.1700
Data Index: 4365299 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.2726. Min Act: -0.1700
Data Index: 4990693 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.2101. Min Act: -0.1700
Data Index: 3669169 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.2101. Min Act: -0.1700
Data Index: 5689424 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.2101. Min Act: -0.1700
Data Index: 4620747 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.1476. Min Act: -0.1700
Data Index: 6314967 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.2101. Min Act: -0.1700
Data Index: 6652293 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0851. Min Act: -0.1700
Data Index: 5900397 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0851. Min Act: -0.1700
Data Index: 5372737 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0851. Min Act: -0.1700
Data Index: 5895623 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0851. Min Act: -0.1700
Data Index: 4915133 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0851. Min Act: -0.1700
Data Index: 734506 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0226. Min Act: -0.1700
Data Index: 3185185 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0851. Min Act: -0.1700
Data Index: 1095996 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.0851. Min Act: -0.1700
Data Index: 2689230 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3976. Min Range: -8.3976
Max Act: 8.1476. Min Act: -0.1700
Data Index: 7661112 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19