Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4619 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.2385. Min Act: -0.1700
Data Index: 2555297 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.1448. Min Act: -0.1700
Data Index: 1294525 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0823. Min Act: -0.1700
Data Index: 2496822 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5920914 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.1135. Min Act: -0.1700
Data Index: 8564158 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.1135. Min Act: -0.1700
Data Index: 8154893 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0823. Min Act: -0.1700
Data Index: 5304524 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0823. Min Act: -0.1700
Data Index: 7987756 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0823. Min Act: -0.1700
Data Index: 7076679 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0823. Min Act: -0.1700
Data Index: 6871529 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0823. Min Act: -0.1700
Data Index: 239919 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 7189591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 6862596 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 4257831 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 760059 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3675915 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3455986 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3408341 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3166004 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2385. Min Range: -5.2385
Max Act: 5.0510. Min Act: -0.1700
Data Index: 6839422 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19