Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4661562 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.1704. Min Act: -0.1700
Data Index: 815931 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.1704. Min Act: -0.1700
Data Index: 8359134 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.1392. Min Act: -0.1700
Data Index: 1976178 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.0767. Min Act: -0.1700
Data Index: 5505528 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.0454. Min Act: -0.1700
Data Index: 959782 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.0142. Min Act: -0.1700
Data Index: 2798968 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1704. Min Range: -5.1704
Max Act: 5.0142. Min Act: -0.1700
Data Index: 6658659 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.9829. Min Act: -0.1700
Data Index: 6726935 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.9517. Min Act: -0.1700
Data Index: 7425660 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.9517. Min Act: -0.1700
Data Index: 3434966 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.9204. Min Act: -0.1700
Data Index: 714863 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.9204. Min Act: -0.1700
Data Index: 2226283 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.8892. Min Act: -0.1700
Data Index: 6329366 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.8892. Min Act: -0.1700
Data Index: 6034765 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.8892. Min Act: -0.1700
Data Index: 7153758 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.8892. Min Act: -0.1700
Data Index: 4262737 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.8579. Min Act: -0.1700
Data Index: 3273416 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.8579. Min Act: -0.1700
Data Index: 2157398 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1704. Min Range: -5.1704
Max Act: 4.8579. Min Act: -0.1700
Data Index: 4400671 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19