Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0187. Min Range: -10.0187
Max Act: 10.0187. Min Act: -0.1700
Data Index: 1423892 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0187. Min Range: -10.0187
Max Act: 9.5187. Min Act: -0.1700
Data Index: 8553807 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0187. Min Range: -10.0187
Max Act: 9.3937. Min Act: -0.1700
Data Index: 1199591 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0187. Min Range: -10.0187
Max Act: 9.3312. Min Act: -0.1700
Data Index: 3908914 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.8937. Min Act: -0.1700
Data Index: 5574085 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.8312. Min Act: -0.1700
Data Index: 7714215 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.8312. Min Act: -0.1700
Data Index: 7457428 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.8312. Min Act: -0.1700
Data Index: 2168431 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.7062. Min Act: -0.1700
Data Index: 2807407 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.7062. Min Act: -0.1700
Data Index: 354809 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.7062. Min Act: -0.1700
Data Index: 8125469 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.5812. Min Act: -0.1700
Data Index: 8361870 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.5187. Min Act: -0.1700
Data Index: 5035542 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.5187. Min Act: -0.1700
Data Index: 2968457 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 695592 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 3064435 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 1747208 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 3936935 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.3937. Min Act: -0.1700
Data Index: 2828339 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0187. Min Range: -10.0187
Max Act: 8.3937. Min Act: -0.1700
Data Index: 6305252 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19