Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2131. Min Range: -4.2131
Max Act: 4.2131. Min Act: -0.1700
Data Index: 4600980 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8693. Min Act: -0.1700
Data Index: 1292476 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.9005. Min Act: -0.1700
Data Index: 90019 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.9005. Min Act: -0.1700
Data Index: 7627380 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8693. Min Act: -0.1700
Data Index: 3998603 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8693. Min Act: -0.1700
Data Index: 4614180 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8380. Min Act: -0.1700
Data Index: 3246992 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5256447 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5453096 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8380. Min Act: -0.1700
Data Index: 1165743 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8380. Min Act: -0.1700
Data Index: 3584346 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8380. Min Act: -0.1700
Data Index: 8728108 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8067. Min Act: -0.1700
Data Index: 4765490 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8067. Min Act: -0.1700
Data Index: 4016358 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8067. Min Act: -0.1700
Data Index: 527509 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8067. Min Act: -0.1700
Data Index: 6826931 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8067. Min Act: -0.1700
Data Index: 1640261 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.8067. Min Act: -0.1700
Data Index: 4991271 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.7754. Min Act: -0.1700
Data Index: 3587551 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2131. Min Range: -4.2131
Max Act: 3.7442. Min Act: -0.1700
Data Index: 3835198 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19