Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.4563. Min Act: -0.1700
Data Index: 570779 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.4563. Min Act: -0.1700
Data Index: 3205791 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3625. Min Act: -0.1700
Data Index: 6492369 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.2688. Min Act: -0.1700
Data Index: 562792 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.2375. Min Act: -0.1700
Data Index: 2903659 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.2375. Min Act: -0.1700
Data Index: 6587023 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.2063. Min Act: -0.1700
Data Index: 453046 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1750. Min Act: -0.1700
Data Index: 3585486 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1750. Min Act: -0.1700
Data Index: 4027212 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1125. Min Act: -0.1700
Data Index: 664202 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1438. Min Act: -0.1700
Data Index: 2527550 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1438. Min Act: -0.1700
Data Index: 754961 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1438. Min Act: -0.1700
Data Index: 2300517 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1438. Min Act: -0.1700
Data Index: 4234527 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1438. Min Act: -0.1700
Data Index: 4467850 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1438. Min Act: -0.1700
Data Index: 4693759 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1438. Min Act: -0.1700
Data Index: 4693751 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1125. Min Act: -0.1700
Data Index: 6101048 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.1125. Min Act: -0.1700
Data Index: 1650855 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.0812. Min Act: -0.1700
Data Index: 3876961 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19