Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.5882. Min Act: -0.1700
Data Index: 5835337 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.3695. Min Act: -0.1700
Data Index: 1296201 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.3695. Min Act: -0.1700
Data Index: 7517765 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.2445. Min Act: -0.1700
Data Index: 2886564 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.2132. Min Act: -0.1700
Data Index: 87028 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.1507. Min Act: -0.1700
Data Index: 694874 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.0882. Min Act: -0.1700
Data Index: 6262459 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.0570. Min Act: -0.1700
Data Index: 6507245 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.1195. Min Act: -0.1700
Data Index: 6913855 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.0570. Min Act: -0.1700
Data Index: 8234870 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.0570. Min Act: -0.1700
Data Index: 2897375 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.0257. Min Act: -0.1700
Data Index: 495539 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.0257. Min Act: -0.1700
Data Index: 7316858 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5882. Min Range: -6.5882
Max Act: 5.9632. Min Act: -0.1700
Data Index: 8218984 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5882. Min Range: -6.5882
Max Act: 6.0257. Min Act: -0.1700
Data Index: 2481688 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5882. Min Range: -6.5882
Max Act: 5.9945. Min Act: -0.1700
Data Index: 7293039 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5882. Min Range: -6.5882
Max Act: 5.9945. Min Act: -0.1700
Data Index: 1367223 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5882. Min Range: -6.5882
Max Act: 5.9632. Min Act: -0.1700
Data Index: 5194330 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5882. Min Range: -6.5882
Max Act: 5.9632. Min Act: -0.1700
Data Index: 5357505 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5882. Min Range: -6.5882
Max Act: 5.9632. Min Act: -0.1700
Data Index: 542667 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19