Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.6385. Min Act: -0.1700
Data Index: 3301965 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.4976. Min Act: -0.1700
Data Index: 8375107 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.4506. Min Act: -0.1700
Data Index: 1260944 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.4036. Min Act: -0.1700
Data Index: 720572 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.4036. Min Act: -0.1700
Data Index: 2386815 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.4036. Min Act: -0.1700
Data Index: 1290267 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.3722. Min Act: -0.1700
Data Index: 3028018 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.3565. Min Act: -0.1700
Data Index: 7017463 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.3408. Min Act: -0.1700
Data Index: 279454 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.3251. Min Act: -0.1700
Data Index: 6107447 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.3095. Min Act: -0.1700
Data Index: 5404929 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.3095. Min Act: -0.1700
Data Index: 837630 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.2938. Min Act: -0.1700
Data Index: 3898969 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.3095. Min Act: -0.1700
Data Index: 2167566 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.2623. Min Act: -0.1700
Data Index: 4205239 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.2309. Min Act: -0.1700
Data Index: 736008 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.2152. Min Act: -0.1700
Data Index: 3524996 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.2309. Min Act: -0.1700
Data Index: 8823589 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.2309. Min Act: -0.1700
Data Index: 6507723 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6385. Min Range: -3.6385
Max Act: 3.2152. Min Act: -0.1700
Data Index: 645190 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19