Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5462 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4099. Min Range: -10.4099
Max Act: 10.4099. Min Act: -0.1700
Data Index: 329891 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4099. Min Range: -10.4099
Max Act: 10.2224. Min Act: -0.1700
Data Index: 2774972 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4099. Min Range: -10.4099
Max Act: 10.0974. Min Act: -0.1700
Data Index: 7066884 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.9724. Min Act: -0.1700
Data Index: 1927515 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.8474. Min Act: -0.1700
Data Index: 4993635 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.8474. Min Act: -0.1700
Data Index: 3751452 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.7849. Min Act: -0.1700
Data Index: 4426259 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.7849. Min Act: -0.1700
Data Index: 3533 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.7224. Min Act: -0.1700
Data Index: 3690513 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.7849. Min Act: -0.1700
Data Index: 2747962 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.7224. Min Act: -0.1700
Data Index: 341074 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 2197514 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 4938237 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 2566649 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.6599. Min Act: -0.1700
Data Index: 5078340 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.5349. Min Act: -0.1700
Data Index: 5650274 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.5349. Min Act: -0.1700
Data Index: 7916355 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.5349. Min Act: -0.1700
Data Index: 4550547 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 3558502 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4099. Min Range: -10.4099
Max Act: 9.4099. Min Act: -0.1700
Data Index: 4722336 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19