Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2325 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.2243. Min Range: -10.2243
Max Act: 10.2243. Min Act: -0.1700
Data Index: 5970219 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2243. Min Range: -10.2243
Max Act: 10.0368. Min Act: -0.1700
Data Index: 5970218 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.4118. Min Act: -0.1700
Data Index: 2038794 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.2243. Min Act: -0.1700
Data Index: 188826 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.2243. Min Act: -0.1700
Data Index: 2303952 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.0993. Min Act: -0.1700
Data Index: 3233000 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.1618. Min Act: -0.1700
Data Index: 741042 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.0993. Min Act: -0.1700
Data Index: 2389129 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.1618. Min Act: -0.1700
Data Index: 3137339 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.0993. Min Act: -0.1700
Data Index: 8349897 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.0993. Min Act: -0.1700
Data Index: 3787334 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2243. Min Range: -10.2243
Max Act: 9.0368. Min Act: -0.1700
Data Index: 4722806 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9743. Min Act: -0.1700
Data Index: 6886524 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9743. Min Act: -0.1700
Data Index: 2850899 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9743. Min Act: -0.1700
Data Index: 1778163 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9743. Min Act: -0.1700
Data Index: 7759452 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9118. Min Act: -0.1700
Data Index: 308484 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9118. Min Act: -0.1700
Data Index: 3893389 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9118. Min Act: -0.1700
Data Index: 1778182 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2243. Min Range: -10.2243
Max Act: 8.9118. Min Act: -0.1700
Data Index: 1927906 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19