Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.8354. Min Act: -0.1700
Data Index: 5698559 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.7729. Min Act: -0.1700
Data Index: 2153945 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.7416. Min Act: -0.1700
Data Index: 6726834 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.7104. Min Act: -0.1700
Data Index: 6437263 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.6791. Min Act: -0.1700
Data Index: 4595962 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.6791. Min Act: -0.1700
Data Index: 1944405 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.6166. Min Act: -0.1700
Data Index: 7598568 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.6166. Min Act: -0.1700
Data Index: 7589020 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.6166. Min Act: -0.1700
Data Index: 8643304 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.6166. Min Act: -0.1700
Data Index: 573835 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5541. Min Act: -0.1700
Data Index: 1317347 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5541. Min Act: -0.1700
Data Index: 3764041 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5541. Min Act: -0.1700
Data Index: 1952609 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5229. Min Act: -0.1700
Data Index: 3795445 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5229. Min Act: -0.1700
Data Index: 3992558 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5229. Min Act: -0.1700
Data Index: 1701032 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5229. Min Act: -0.1700
Data Index: 8407137 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.5229. Min Act: -0.1700
Data Index: 6951278 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.4916. Min Act: -0.1700
Data Index: 3810270 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8354. Min Range: -5.8354
Max Act: 5.4916. Min Act: -0.1700
Data Index: 6754419 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19