Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2332. Min Range: -7.2332
Max Act: 7.2332. Min Act: -0.1700
Data Index: 5963684 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2332. Min Range: -7.2332
Max Act: 7.2332. Min Act: -0.1700
Data Index: 554920 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2332. Min Range: -7.2332
Max Act: 7.1082. Min Act: -0.1700
Data Index: 7852747 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2332. Min Range: -7.2332
Max Act: 7.0457. Min Act: -0.1700
Data Index: 1067277 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2332. Min Range: -7.2332
Max Act: 7.0145. Min Act: -0.1700
Data Index: 7434362 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.9520. Min Act: -0.1699
Data Index: 6536241 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.9520. Min Act: -0.1700
Data Index: 4591871 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.9520. Min Act: -0.1700
Data Index: 4200449 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.9520. Min Act: -0.1700
Data Index: 1579504 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.9207. Min Act: -0.1700
Data Index: 8261334 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8895. Min Act: -0.1700
Data Index: 4212526 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.9207. Min Act: -0.1700
Data Index: 4192190 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8895. Min Act: -0.1700
Data Index: 5131142 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8582. Min Act: -0.1700
Data Index: 3670207 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8582. Min Act: -0.1700
Data Index: 2603751 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8582. Min Act: -0.1700
Data Index: 5520529 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8582. Min Act: -0.1700
Data Index: 4277658 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8270. Min Act: -0.1700
Data Index: 4753307 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.8270. Min Act: -0.1700
Data Index: 5217027 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2332. Min Range: -7.2332
Max Act: 6.7957. Min Act: -0.1700
Data Index: 3971218 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19