Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2324 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.7081. Min Act: -0.1700
Data Index: 5559414 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.7081. Min Act: -0.1700
Data Index: 4483639 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.5206. Min Act: -0.1700
Data Index: 7116704 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.4894. Min Act: -0.1700
Data Index: 7416624 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.4581. Min Act: -0.1700
Data Index: 7332178 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.4269. Min Act: -0.1700
Data Index: 5370969 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.4269. Min Act: -0.1700
Data Index: 4377555 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.4269. Min Act: -0.1700
Data Index: 8484786 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3331. Min Act: -0.1700
Data Index: 1244311 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3644. Min Act: -0.1700
Data Index: 4038200 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3331. Min Act: -0.1700
Data Index: 3845986 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3331. Min Act: -0.1700
Data Index: 5679531 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2706. Min Act: -0.1700
Data Index: 8287849 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3019. Min Act: -0.1700
Data Index: 826589 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3019. Min Act: -0.1700
Data Index: 6264507 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.3019. Min Act: -0.1700
Data Index: 1960272 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2706. Min Act: -0.1700
Data Index: 5209986 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2706. Min Act: -0.1700
Data Index: 1918788 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2394. Min Act: -0.1700
Data Index: 5238800 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7081. Min Range: -6.7081
Max Act: 6.2394. Min Act: -0.1700
Data Index: 2060927 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19