Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.5379. Min Act: -0.1700
Data Index: 5444515 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.5066. Min Act: -0.1700
Data Index: 7084376 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.4754. Min Act: -0.1700
Data Index: 8510215 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.3816. Min Act: -0.1700
Data Index: 3690664 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.3504. Min Act: -0.1700
Data Index: 6446723 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.3191. Min Act: -0.1700
Data Index: 5632241 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.3191. Min Act: -0.1700
Data Index: 1788919 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2566. Min Act: -0.1700
Data Index: 5195513 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2879. Min Act: -0.1700
Data Index: 3886541 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2566. Min Act: -0.1700
Data Index: 8185695 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2566. Min Act: -0.1700
Data Index: 7294196 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2254. Min Act: -0.1700
Data Index: 2202600 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.1941. Min Act: -0.1700
Data Index: 1638436 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2254. Min Act: -0.1700
Data Index: 2228104 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.1941. Min Act: -0.1700
Data Index: 2949873 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2254. Min Act: -0.1700
Data Index: 7749634 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.2254. Min Act: -0.1700
Data Index: 21920 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.1629. Min Act: -0.1700
Data Index: 7783458 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.1629. Min Act: -0.1700
Data Index: 4864140 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5379. Min Range: -5.5379
Max Act: 5.1629. Min Act: -0.1700
Data Index: 1232441 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19