Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0673. Min Range: -3.0673
Max Act: 3.0673. Min Act: -0.1700
Data Index: 7978751 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0673. Min Range: -3.0673
Max Act: 3.0515. Min Act: -0.1700
Data Index: 1856713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.9725. Min Act: -0.1700
Data Index: 7178245 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.9725. Min Act: -0.1700
Data Index: 7702711 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.9092. Min Act: -0.1700
Data Index: 4887910 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.9092. Min Act: -0.1700
Data Index: 2306668 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8775. Min Act: -0.1700
Data Index: 7478962 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8616. Min Act: -0.1700
Data Index: 4613115 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8457. Min Act: -0.1700
Data Index: 6400828 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8457. Min Act: -0.1700
Data Index: 5610625 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8457. Min Act: -0.1700
Data Index: 4398213 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8457. Min Act: -0.1700
Data Index: 8274310 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8457. Min Act: -0.1700
Data Index: 2452610 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8298. Min Act: -0.1700
Data Index: 3522267 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8457. Min Act: -0.1700
Data Index: 8263000 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8298. Min Act: -0.1700
Data Index: 6352180 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8139. Min Act: -0.1700
Data Index: 2873994 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.7980. Min Act: -0.1700
Data Index: 5802716 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.8298. Min Act: -0.1700
Data Index: 4175436 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0673. Min Range: -3.0673
Max Act: 2.7980. Min Act: -0.1700
Data Index: 5118066 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19