Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.8494. Min Act: -0.1700
Data Index: 966404 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.6931. Min Act: -0.1700
Data Index: 4120984 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5994. Min Act: -0.1700
Data Index: 7662111 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5994. Min Act: -0.1700
Data Index: 7331420 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5681. Min Act: -0.1700
Data Index: 2652627 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5369. Min Act: -0.1699
Data Index: 817169 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5994. Min Act: -0.1700
Data Index: 6585138 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5681. Min Act: -0.1700
Data Index: 3429020 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5056. Min Act: -0.1700
Data Index: 8766661 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5056. Min Act: -0.1700
Data Index: 545959 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4744. Min Act: -0.1700
Data Index: 8616866 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4744. Min Act: -0.1700
Data Index: 1267613 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4744. Min Act: -0.1700
Data Index: 2108324 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.5056. Min Act: -0.1700
Data Index: 5254750 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4744. Min Act: -0.1700
Data Index: 3461113 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4744. Min Act: -0.1700
Data Index: 287788 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4744. Min Act: -0.1700
Data Index: 4455355 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4744. Min Act: -0.1700
Data Index: 3184805 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4431. Min Act: -0.1700
Data Index: 3922249 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8494. Min Range: -5.8494
Max Act: 5.4431. Min Act: -0.1700
Data Index: 7642631 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19