Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.8246. Min Act: -0.1700
Data Index: 6752712 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.7934. Min Act: -0.1700
Data Index: 6095265 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.7309. Min Act: -0.1700
Data Index: 6037083 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.6059. Min Act: -0.1700
Data Index: 4221417 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.6059. Min Act: -0.1700
Data Index: 8062617 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.6059. Min Act: -0.1700
Data Index: 6858869 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.6059. Min Act: -0.1700
Data Index: 5261435 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.5746. Min Act: -0.1700
Data Index: 7085681 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.5746. Min Act: -0.1700
Data Index: 7101768 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.5121. Min Act: -0.1700
Data Index: 2173195 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.5121. Min Act: -0.1700
Data Index: 7954717 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.4809. Min Act: -0.1700
Data Index: 8328932 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.4809. Min Act: -0.1700
Data Index: 4059732 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.4809. Min Act: -0.1700
Data Index: 4401986 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.4496. Min Act: -0.1700
Data Index: 3460341 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.4184. Min Act: -0.1700
Data Index: 924056 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.3871. Min Act: -0.1700
Data Index: 1046009 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.4184. Min Act: -0.1700
Data Index: 4301648 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.3871. Min Act: -0.1700
Data Index: 7189720 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8246. Min Range: -7.8246
Max Act: 7.3871. Min Act: -0.1700
Data Index: 3848746 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19