Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.8142. Min Act: -0.1700
Data Index: 8382992 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.7204. Min Act: -0.1700
Data Index: 1935316 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.7204. Min Act: -0.1700
Data Index: 2561417 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.6892. Min Act: -0.1700
Data Index: 4265489 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5954. Min Act: -0.1700
Data Index: 213928 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5954. Min Act: -0.1700
Data Index: 2310383 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5642. Min Act: -0.1700
Data Index: 3823304 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5642. Min Act: -0.1700
Data Index: 2791043 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5017. Min Act: -0.1700
Data Index: 6347442 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5329. Min Act: -0.1700
Data Index: 5871667 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5329. Min Act: -0.1700
Data Index: 8102523 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5017. Min Act: -0.1700
Data Index: 1273595 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5017. Min Act: -0.1700
Data Index: 1262156 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5017. Min Act: -0.1700
Data Index: 1902736 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5017. Min Act: -0.1700
Data Index: 243580 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5017. Min Act: -0.1700
Data Index: 5941575 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.5017. Min Act: -0.1700
Data Index: 8039274 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.4704. Min Act: -0.1700
Data Index: 3305029 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.4704. Min Act: -0.1700
Data Index: 342829 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8142. Min Range: -5.8142
Max Act: 5.4704. Min Act: -0.1700
Data Index: 5678201 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19