Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2193. Min Range: -5.2193
Max Act: 5.2193. Min Act: -0.1700
Data Index: 6775295 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2193. Min Range: -5.2193
Max Act: 5.0318. Min Act: -0.1700
Data Index: 3638394 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2193. Min Range: -5.2193
Max Act: 5.0005. Min Act: -0.1700
Data Index: 6653832 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.9380. Min Act: -0.1700
Data Index: 6586912 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8755. Min Act: -0.1700
Data Index: 8027217 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.9068. Min Act: -0.1700
Data Index: 8196790 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8755. Min Act: -0.1700
Data Index: 423980 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8443. Min Act: -0.1700
Data Index: 3407677 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8443. Min Act: -0.1700
Data Index: 1415256 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8130. Min Act: -0.1700
Data Index: 3292512 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8130. Min Act: -0.1700
Data Index: 7145110 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8130. Min Act: -0.1700
Data Index: 3641338 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.7818. Min Act: -0.1700
Data Index: 3611017 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8130. Min Act: -0.1700
Data Index: 2367041 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.7818. Min Act: -0.1700
Data Index: 6574203 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.7818. Min Act: -0.1700
Data Index: 1671402 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.7818. Min Act: -0.1700
Data Index: 746301 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.7818. Min Act: -0.1700
Data Index: 4243000 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.8130. Min Act: -0.1700
Data Index: 4905210 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2193. Min Range: -5.2193
Max Act: 4.7505. Min Act: -0.1700
Data Index: 5491644 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19