Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.7518. Min Act: -0.1700
Data Index: 4231519 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.7206. Min Act: -0.1700
Data Index: 7464139 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.6581. Min Act: -0.1700
Data Index: 465340 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.6581. Min Act: -0.1700
Data Index: 307818 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.6581. Min Act: -0.1700
Data Index: 3938545 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.6268. Min Act: -0.1700
Data Index: 4827728 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.6268. Min Act: -0.1700
Data Index: 2925472 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5643. Min Act: -0.1700
Data Index: 4243293 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5956. Min Act: -0.1700
Data Index: 2000973 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5956. Min Act: -0.1700
Data Index: 165106 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5956. Min Act: -0.1700
Data Index: 7704215 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5643. Min Act: -0.1700
Data Index: 5472353 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5956. Min Act: -0.1700
Data Index: 2455776 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5643. Min Act: -0.1700
Data Index: 2981097 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5643. Min Act: -0.1700
Data Index: 6707079 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5331. Min Act: -0.1700
Data Index: 779373 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5956. Min Act: -0.1700
Data Index: 2408079 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5018. Min Act: -0.1700
Data Index: 6682269 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5331. Min Act: -0.1700
Data Index: 528000 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7518. Min Range: -5.7518
Max Act: 5.5331. Min Act: -0.1700
Data Index: 3509053 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19