Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5531. Min Range: -7.5531
Max Act: 7.5531. Min Act: -0.1700
Data Index: 4238627 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.8344. Min Act: -0.1700
Data Index: 330724 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.6781. Min Act: -0.1700
Data Index: 8020249 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.6781. Min Act: -0.1700
Data Index: 1721786 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.5844. Min Act: -0.1700
Data Index: 6787244 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.6156. Min Act: -0.1700
Data Index: 3037872 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.5531. Min Act: -0.1700
Data Index: 3986363 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.5531. Min Act: -0.1700
Data Index: 2094999 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.5531. Min Act: -0.1700
Data Index: 2218223 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.5219. Min Act: -0.1700
Data Index: 1766231 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.5219. Min Act: -0.1700
Data Index: 3569463 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.4594. Min Act: -0.1700
Data Index: 3376448 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.3969. Min Act: -0.1700
Data Index: 8587362 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.4281. Min Act: -0.1700
Data Index: 8210255 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.3969. Min Act: -0.1700
Data Index: 1493618 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.3969. Min Act: -0.1700
Data Index: 4661508 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.3656. Min Act: -0.1700
Data Index: 4135492 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.3656. Min Act: -0.1700
Data Index: 2182783 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.3656. Min Act: -0.1700
Data Index: 7993168 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5531. Min Range: -7.5531
Max Act: 6.3344. Min Act: -0.1700
Data Index: 828336 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19