Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5798 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2046. Min Range: -5.2046
Max Act: 5.2046. Min Act: -0.1700
Data Index: 6668095 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2046. Min Range: -5.2046
Max Act: 5.1108. Min Act: -0.1700
Data Index: 320422 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2046. Min Range: -5.2046
Max Act: 5.1108. Min Act: -0.1700
Data Index: 4923890 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.8921. Min Act: -0.1700
Data Index: 8516228 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.8608. Min Act: -0.1700
Data Index: 3898052 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.8608. Min Act: -0.1700
Data Index: 1237206 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.8296. Min Act: -0.1700
Data Index: 5579633 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7983. Min Act: -0.1700
Data Index: 7878601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.8296. Min Act: -0.1700
Data Index: 2004828 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7983. Min Act: -0.1700
Data Index: 3142914 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7983. Min Act: -0.1700
Data Index: 6003433 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7671. Min Act: -0.1700
Data Index: 8457837 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7983. Min Act: -0.1700
Data Index: 8584192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7983. Min Act: -0.1700
Data Index: 1798215 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7671. Min Act: -0.1700
Data Index: 4951972 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7671. Min Act: -0.1700
Data Index: 8559029 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7358. Min Act: -0.1700
Data Index: 4634566 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7046. Min Act: -0.1700
Data Index: 179922 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7046. Min Act: -0.1700
Data Index: 2208091 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2046. Min Range: -5.2046
Max Act: 4.7046. Min Act: -0.1700
Data Index: 6419836 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19