Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2263 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.5209. Min Act: -0.1700
Data Index: 7420322 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.3021. Min Act: -0.1700
Data Index: 6343548 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.2709. Min Act: -0.1700
Data Index: 4232339 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.2084. Min Act: -0.1700
Data Index: 7365941 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1771. Min Act: -0.1700
Data Index: 1783557 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1771. Min Act: -0.1700
Data Index: 1349774 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6084258 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1771. Min Act: -0.1700
Data Index: 159148 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1771. Min Act: -0.1700
Data Index: 7795146 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1459. Min Act: -0.1700
Data Index: 7943886 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0834. Min Act: -0.1700
Data Index: 5836620 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.1146. Min Act: -0.1700
Data Index: 4238246 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0521. Min Act: -0.1700
Data Index: 3865974 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0521. Min Act: -0.1700
Data Index: 6717009 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0209. Min Act: -0.1700
Data Index: 5278016 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5209. Min Range: -6.5209
Max Act: 6.0209. Min Act: -0.1700
Data Index: 8443581 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.9896. Min Act: -0.1700
Data Index: 3350652 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.9896. Min Act: -0.1700
Data Index: 1372370 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.9896. Min Act: -0.1700
Data Index: 1086382 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5209. Min Range: -6.5209
Max Act: 5.9584. Min Act: -0.1700
Data Index: 1225734 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19