Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 636 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.9359. Min Act: -0.1700
Data Index: 2592314 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.8734. Min Act: -0.1700
Data Index: 3275982 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.7797. Min Act: -0.1700
Data Index: 1922933 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.7484. Min Act: -0.1700
Data Index: 170714 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.7484. Min Act: -0.1700
Data Index: 2459011 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.7172. Min Act: -0.1700
Data Index: 8519687 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.6547. Min Act: -0.1700
Data Index: 1308084 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5922. Min Act: -0.1700
Data Index: 7084680 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.6234. Min Act: -0.1700
Data Index: 8259568 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.6234. Min Act: -0.1700
Data Index: 7267494 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.6234. Min Act: -0.1700
Data Index: 1889229 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5922. Min Act: -0.1700
Data Index: 342125 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5922. Min Act: -0.1700
Data Index: 125916 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5609. Min Act: -0.1700
Data Index: 6505235 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5609. Min Act: -0.1700
Data Index: 7732761 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5609. Min Act: -0.1700
Data Index: 4729032 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5609. Min Act: -0.1700
Data Index: 8543624 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5297. Min Act: -0.1700
Data Index: 3380042 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.5297. Min Act: -0.1700
Data Index: 7832426 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9359. Min Range: -6.9359
Max Act: 6.4984. Min Act: -0.1700
Data Index: 638250 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19