Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4125 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.3004. Min Act: -0.1700
Data Index: 1880607 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.3004. Min Act: -0.1700
Data Index: 7348209 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7348208 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4611577 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.1441. Min Act: -0.1700
Data Index: 471643 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.1129. Min Act: -0.1700
Data Index: 536308 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.1129. Min Act: -0.1700
Data Index: 6107145 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.0816. Min Act: -0.1700
Data Index: 7646308 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.0816. Min Act: -0.1700
Data Index: 69857 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3004. Min Range: -5.3004
Max Act: 5.0191. Min Act: -0.1700
Data Index: 8001280 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.9879. Min Act: -0.1700
Data Index: 5952916 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.9566. Min Act: -0.1700
Data Index: 8433584 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.9254. Min Act: -0.1700
Data Index: 3657022 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.9254. Min Act: -0.1700
Data Index: 8353114 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.8629. Min Act: -0.1700
Data Index: 4091618 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.8316. Min Act: -0.1700
Data Index: 5130756 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.8629. Min Act: -0.1700
Data Index: 7983659 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.8316. Min Act: -0.1700
Data Index: 5318799 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.8316. Min Act: -0.1700
Data Index: 1862481 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3004. Min Range: -5.3004
Max Act: 4.8316. Min Act: -0.1700
Data Index: 7137406 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19