Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.8998. Min Act: -0.1700
Data Index: 4842294 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.7123. Min Act: -0.1700
Data Index: 6689443 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.6498. Min Act: -0.1700
Data Index: 5923019 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.6185. Min Act: -0.1700
Data Index: 1818433 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.5873. Min Act: -0.1700
Data Index: 6818405 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.5873. Min Act: -0.1700
Data Index: 7475635 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.5248. Min Act: -0.1700
Data Index: 6250089 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.5248. Min Act: -0.1700
Data Index: 4999992 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.5248. Min Act: -0.1700
Data Index: 3167044 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.4623. Min Act: -0.1700
Data Index: 7921501 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.4623. Min Act: -0.1700
Data Index: 5600002 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.4623. Min Act: -0.1700
Data Index: 6536115 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.4310. Min Act: -0.1700
Data Index: 3190200 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.4310. Min Act: -0.1700
Data Index: 1355208 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.3998. Min Act: -0.1700
Data Index: 1371200 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.3998. Min Act: -0.1700
Data Index: 7363029 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.3685. Min Act: -0.1700
Data Index: 2727284 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.3373. Min Act: -0.1700
Data Index: 2450456 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.3373. Min Act: -0.1700
Data Index: 252187 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8998. Min Range: -7.8998
Max Act: 7.3373. Min Act: -0.1700
Data Index: 5188579 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19