Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.6753. Min Act: -0.1700
Data Index: 7329104 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.5503. Min Act: -0.1700
Data Index: 6385579 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.4878. Min Act: -0.1700
Data Index: 324215 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.4878. Min Act: -0.1700
Data Index: 8345282 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.4565. Min Act: -0.1700
Data Index: 523852 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.4565. Min Act: -0.1700
Data Index: 4863298 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.4253. Min Act: -0.1700
Data Index: 1511665 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.4253. Min Act: -0.1700
Data Index: 7461306 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3940. Min Act: -0.1700
Data Index: 8109368 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3315. Min Act: -0.1700
Data Index: 883055 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3628. Min Act: -0.1700
Data Index: 6194 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3628. Min Act: -0.1700
Data Index: 1136972 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3003. Min Act: -0.1700
Data Index: 2265834 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3628. Min Act: -0.1700
Data Index: 5009808 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3003. Min Act: -0.1700
Data Index: 1761287 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3003. Min Act: -0.1700
Data Index: 8204710 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3003. Min Act: -0.1700
Data Index: 8282573 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3003. Min Act: -0.1700
Data Index: 5883209 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3003. Min Act: -0.1700
Data Index: 1997922 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6753. Min Range: -5.6753
Max Act: 5.3003. Min Act: -0.1700
Data Index: 7406402 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19