Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2433 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.3397. Min Act: -0.1700
Data Index: 5366562 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.2459. Min Act: -0.1700
Data Index: 7958661 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.2147. Min Act: -0.1700
Data Index: 1641656 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.2147. Min Act: -0.1700
Data Index: 5548019 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1834. Min Act: -0.1700
Data Index: 8402835 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1522. Min Act: -0.1700
Data Index: 546905 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1522. Min Act: -0.1700
Data Index: 1548534 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1522. Min Act: -0.1700
Data Index: 2047119 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1209. Min Act: -0.1700
Data Index: 3729362 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1209. Min Act: -0.1700
Data Index: 4541744 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0897. Min Act: -0.1700
Data Index: 2571072 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0897. Min Act: -0.1700
Data Index: 3198672 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0584. Min Act: -0.1700
Data Index: 3106513 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0584. Min Act: -0.1700
Data Index: 4733619 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0584. Min Act: -0.1700
Data Index: 6654494 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0584. Min Act: -0.1700
Data Index: 1013358 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0897. Min Act: -0.1700
Data Index: 5118854 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0584. Min Act: -0.1700
Data Index: 4745341 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0272. Min Act: -0.1700
Data Index: 4406734 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0272. Min Act: -0.1700
Data Index: 2388804 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19