Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2471 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7635. Min Act: -0.1700
Data Index: 5147571 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7635. Min Act: -0.1700
Data Index: 834934 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7635. Min Act: -0.1700
Data Index: 7053326 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7476. Min Act: -0.1700
Data Index: 1137011 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7316. Min Act: -0.1700
Data Index: 606097 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7316. Min Act: -0.1700
Data Index: 4973429 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7156. Min Act: -0.1700
Data Index: 6127132 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7156. Min Act: -0.1700
Data Index: 1790620 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7156. Min Act: -0.1700
Data Index: 7652109 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7156. Min Act: -0.1700
Data Index: 7018377 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.7156. Min Act: -0.1700
Data Index: 2313671 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6996. Min Act: -0.1700
Data Index: 4132956 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6996. Min Act: -0.1700
Data Index: 4172600 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6996. Min Act: -0.1700
Data Index: 1591301 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6996. Min Act: -0.1700
Data Index: 8076338 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6996. Min Act: -0.1700
Data Index: 4955385 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6996. Min Act: -0.1700
Data Index: 7568241 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6996. Min Act: -0.1700
Data Index: 1400151 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6836. Min Act: -0.1700
Data Index: 5054609 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7635. Min Range: -2.7635
Max Act: 2.6836. Min Act: -0.1700
Data Index: 5085869 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19