Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5698 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 2159654 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 7372799 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.6539. Min Act: -0.1700
Data Index: 741619 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.5602. Min Act: -0.1700
Data Index: 2159659 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.5914. Min Act: -0.1700
Data Index: 2257753 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.5289. Min Act: -0.1700
Data Index: 2236116 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.5289. Min Act: -0.1700
Data Index: 5385771 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.5289. Min Act: -0.1700
Data Index: 4119843 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4977. Min Act: -0.1700
Data Index: 2777062 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4977. Min Act: -0.1700
Data Index: 5490510 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4664. Min Act: -0.1700
Data Index: 2160325 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4664. Min Act: -0.1700
Data Index: 5772172 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4664. Min Act: -0.1700
Data Index: 1342327 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1589983 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4352. Min Act: -0.1700
Data Index: 348700 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4352. Min Act: -0.1700
Data Index: 5129316 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4352. Min Act: -0.1700
Data Index: 1351307 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4352. Min Act: -0.1700
Data Index: 464423 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4352. Min Act: -0.1700
Data Index: 6896550 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7477. Min Range: -5.7477
Max Act: 5.4352. Min Act: -0.1700
Data Index: 2839761 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19