Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.9212. Min Act: -0.1700
Data Index: 8807170 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.8587. Min Act: -0.1700
Data Index: 8662936 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.7650. Min Act: -0.1700
Data Index: 4787215 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.7337. Min Act: -0.1700
Data Index: 7003296 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.7025. Min Act: -0.1700
Data Index: 8479506 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.7025. Min Act: -0.1700
Data Index: 979936 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.6712. Min Act: -0.1700
Data Index: 8153705 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.6712. Min Act: -0.1700
Data Index: 8025997 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.6712. Min Act: -0.1700
Data Index: 4752318 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.6712. Min Act: -0.1700
Data Index: 8776368 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.6400. Min Act: -0.1700
Data Index: 4156731 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.6400. Min Act: -0.1700
Data Index: 1080306 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5775. Min Act: -0.1700
Data Index: 1076420 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5775. Min Act: -0.1700
Data Index: 577864 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5775. Min Act: -0.1700
Data Index: 1479274 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5775. Min Act: -0.1700
Data Index: 7940709 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5775. Min Act: -0.1700
Data Index: 7498593 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5775. Min Act: -0.1700
Data Index: 3708301 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5150. Min Act: -0.1700
Data Index: 8508599 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9212. Min Range: -5.9212
Max Act: 5.5150. Min Act: -0.1700
Data Index: 201676 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19