Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5312 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4314. Min Range: -6.4314
Max Act: 6.4314. Min Act: -0.1700
Data Index: 7342936 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4314. Min Range: -6.4314
Max Act: 6.3064. Min Act: -0.1700
Data Index: 7056793 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4314. Min Range: -6.4314
Max Act: 6.1189. Min Act: -0.1700
Data Index: 6121808 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4314. Min Range: -6.4314
Max Act: 6.0876. Min Act: -0.1700
Data Index: 8653597 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4314. Min Range: -6.4314
Max Act: 6.0564. Min Act: -0.1700
Data Index: 7941936 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9939. Min Act: -0.1700
Data Index: 8527444 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4314. Min Range: -6.4314
Max Act: 6.0564. Min Act: -0.1700
Data Index: 4992646 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9939. Min Act: -0.1700
Data Index: 1119600 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9626. Min Act: -0.1700
Data Index: 4646790 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9626. Min Act: -0.1700
Data Index: 4872951 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9626. Min Act: -0.1700
Data Index: 6986293 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9626. Min Act: -0.1700
Data Index: 1119599 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.8689. Min Act: -0.1700
Data Index: 4795801 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9001. Min Act: -0.1700
Data Index: 7237192 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9001. Min Act: -0.1700
Data Index: 7941935 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9314. Min Act: -0.1700
Data Index: 6196635 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.9001. Min Act: -0.1700
Data Index: 858234 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.8689. Min Act: -0.1700
Data Index: 5916661 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.8376. Min Act: -0.1700
Data Index: 3108166 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4314. Min Range: -6.4314
Max Act: 5.8064. Min Act: -0.1700
Data Index: 3056781 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19