Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2859 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.4429. Min Act: -0.1700
Data Index: 7182227 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.1617. Min Act: -0.1700
Data Index: 6065905 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0679. Min Act: -0.1700
Data Index: 916974 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0054. Min Act: -0.1700
Data Index: 1806918 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.8179. Min Act: -0.1700
Data Index: 1950330 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.8492. Min Act: -0.1700
Data Index: 3033988 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.8492. Min Act: -0.1700
Data Index: 561151 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.7867. Min Act: -0.1700
Data Index: 1902564 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.8179. Min Act: -0.1700
Data Index: 2371081 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.7242. Min Act: -0.1700
Data Index: 8589878 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.7554. Min Act: -0.1700
Data Index: 4857312 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.6617. Min Act: -0.1700
Data Index: 2921041 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.6929. Min Act: -0.1700
Data Index: 288294 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.6304. Min Act: -0.1700
Data Index: 733899 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.6304. Min Act: -0.1700
Data Index: 177508 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.6304. Min Act: -0.1700
Data Index: 3127900 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.6617. Min Act: -0.1700
Data Index: 8310869 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.6617. Min Act: -0.1700
Data Index: 810481 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.5992. Min Act: -0.1700
Data Index: 7601544 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4109951 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19