Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3942 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0095. Min Range: -6.0095
Max Act: 6.0095. Min Act: -0.1700
Data Index: 328849 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0095. Min Range: -6.0095
Max Act: 6.0095. Min Act: -0.1700
Data Index: 7896522 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.9782. Min Act: -0.1700
Data Index: 7402072 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.9470. Min Act: -0.1700
Data Index: 4019718 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.8845. Min Act: -0.1700
Data Index: 6890352 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.8845. Min Act: -0.1700
Data Index: 2321591 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.8220. Min Act: -0.1700
Data Index: 5269569 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.8532. Min Act: -0.1700
Data Index: 1464707 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7907. Min Act: -0.1700
Data Index: 101493 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7595. Min Act: -0.1700
Data Index: 7911320 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7282. Min Act: -0.1700
Data Index: 1258761 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7282. Min Act: -0.1700
Data Index: 380608 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 7620947 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 7824034 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 4451776 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 2862055 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6657. Min Act: -0.1700
Data Index: 2463352 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 5801847 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 6892832 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 497382 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19