Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3158. Min Range: -7.3158
Max Act: 7.3158. Min Act: -0.1700
Data Index: 3312653 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3158. Min Range: -7.3158
Max Act: 7.2220. Min Act: -0.1700
Data Index: 819478 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3158. Min Range: -7.3158
Max Act: 7.1283. Min Act: -0.1700
Data Index: 8592344 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3158. Min Range: -7.3158
Max Act: 7.0658. Min Act: -0.1700
Data Index: 7633857 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9720. Min Act: -0.1700
Data Index: 5127286 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9720. Min Act: -0.1700
Data Index: 3312656 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9720. Min Act: -0.1700
Data Index: 8592342 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9720. Min Act: -0.1700
Data Index: 6355572 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9720. Min Act: -0.1700
Data Index: 6355574 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9720. Min Act: -0.1700
Data Index: 8592343 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9408. Min Act: -0.1700
Data Index: 3673802 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9408. Min Act: -0.1700
Data Index: 8228075 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.8783. Min Act: -0.1700
Data Index: 8592345 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.9095. Min Act: -0.1700
Data Index: 6865197 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.8783. Min Act: -0.1700
Data Index: 8592346 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.8783. Min Act: -0.1700
Data Index: 453659 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.8470. Min Act: -0.1700
Data Index: 3673803 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.8470. Min Act: -0.1700
Data Index: 3539730 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.8158. Min Act: -0.1700
Data Index: 973804 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3158. Min Range: -7.3158
Max Act: 6.7845. Min Act: -0.1700
Data Index: 6865198 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19