Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0972. Min Range: -7.0972
Max Act: 7.0972. Min Act: -0.1700
Data Index: 1685125 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0972. Min Range: -7.0972
Max Act: 7.0972. Min Act: -0.1700
Data Index: 8392629 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.9722. Min Act: -0.1700
Data Index: 306820 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.9410. Min Act: -0.1700
Data Index: 3356388 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.9410. Min Act: -0.1700
Data Index: 1927342 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.9097. Min Act: -0.1700
Data Index: 4554294 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.9097. Min Act: -0.1700
Data Index: 7603110 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.8785. Min Act: -0.1700
Data Index: 6375390 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.8160. Min Act: -0.1700
Data Index: 3368876 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.8472. Min Act: -0.1700
Data Index: 7021721 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.8472. Min Act: -0.1700
Data Index: 5953460 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.8785. Min Act: -0.1700
Data Index: 6532778 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.8472. Min Act: -0.1700
Data Index: 2337461 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.8160. Min Act: -0.1700
Data Index: 7492380 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.7847. Min Act: -0.1700
Data Index: 507492 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.7535. Min Act: -0.1700
Data Index: 4755172 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.7535. Min Act: -0.1700
Data Index: 647455 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.7535. Min Act: -0.1700
Data Index: 3336721 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.7535. Min Act: -0.1700
Data Index: 8350336 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0972. Min Range: -7.0972
Max Act: 6.7222. Min Act: -0.1700
Data Index: 3141500 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19