Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4394 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.9433. Min Act: -0.1700
Data Index: 4688675 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.9433. Min Act: -0.1700
Data Index: 5130719 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.8183. Min Act: -0.1700
Data Index: 4299450 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7871. Min Act: -0.1700
Data Index: 6324166 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7871. Min Act: -0.1700
Data Index: 8342622 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7558. Min Act: -0.1700
Data Index: 8338020 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.8183. Min Act: -0.1700
Data Index: 8027849 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7558. Min Act: -0.1700
Data Index: 5376310 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7558. Min Act: -0.1700
Data Index: 3360830 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7246. Min Act: -0.1700
Data Index: 4920432 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7246. Min Act: -0.1700
Data Index: 3428479 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7246. Min Act: -0.1700
Data Index: 3125009 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7246. Min Act: -0.1700
Data Index: 8277562 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7246. Min Act: -0.1700
Data Index: 6160734 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.7246. Min Act: -0.1700
Data Index: 1718095 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.6933. Min Act: -0.1700
Data Index: 4166108 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.6933. Min Act: -0.1700
Data Index: 8089877 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.6933. Min Act: -0.1700
Data Index: 1562746 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.6933. Min Act: -0.1700
Data Index: 6883878 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9433. Min Range: -5.9433
Max Act: 5.6933. Min Act: -0.1700
Data Index: 5882119 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19