Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2492. Min Act: -0.1700
Data Index: 1830349 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.1554. Min Act: -0.1700
Data Index: 5387068 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.1554. Min Act: -0.1700
Data Index: 7539924 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.0929. Min Act: -0.1700
Data Index: 6688638 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.0617. Min Act: -0.1700
Data Index: 4561240 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9991. Min Act: -0.1700
Data Index: 624959 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9991. Min Act: -0.1700
Data Index: 3479477 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9679. Min Act: -0.1700
Data Index: 935680 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9679. Min Act: -0.1700
Data Index: 8645217 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9679. Min Act: -0.1700
Data Index: 1947688 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9679. Min Act: -0.1700
Data Index: 7495884 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9054. Min Act: -0.1700
Data Index: 5739828 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9054. Min Act: -0.1700
Data Index: 2569967 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9054. Min Act: -0.1700
Data Index: 8539679 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9054. Min Act: -0.1700
Data Index: 388123 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9054. Min Act: -0.1700
Data Index: 1496339 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9054. Min Act: -0.1700
Data Index: 3818299 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9366. Min Act: -0.1700
Data Index: 1750337 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.8741. Min Act: -0.1700
Data Index: 4170522 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2492. Min Range: -4.2492
Max Act: 3.9054. Min Act: -0.1700
Data Index: 2043434 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19