Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.6854. Min Act: -0.1700
Data Index: 8413705 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.6229. Min Act: -0.1700
Data Index: 6365811 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.5292. Min Act: -0.1700
Data Index: 4714074 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.4979. Min Act: -0.1700
Data Index: 5589599 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.4354. Min Act: -0.1700
Data Index: 5150563 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.3729. Min Act: -0.1700
Data Index: 6282012 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.3417. Min Act: -0.1700
Data Index: 8063292 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.3417. Min Act: -0.1700
Data Index: 7229385 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.2479. Min Act: -0.1700
Data Index: 3462234 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.2479. Min Act: -0.1700
Data Index: 7229384 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.2167. Min Act: -0.1700
Data Index: 4177772 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.2167. Min Act: -0.1700
Data Index: 5753496 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.2167. Min Act: -0.1700
Data Index: 8713346 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.1542. Min Act: -0.1700
Data Index: 6293381 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.1229. Min Act: -0.1700
Data Index: 706843 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.1542. Min Act: -0.1700
Data Index: 1509095 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.1542. Min Act: -0.1700
Data Index: 4883923 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.1229. Min Act: -0.1700
Data Index: 7058620 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.1229. Min Act: -0.1700
Data Index: 4651897 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6854. Min Range: -6.6854
Max Act: 6.1229. Min Act: -0.1700
Data Index: 1633293 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19