Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.2299. Min Act: -0.1700
Data Index: 1724939 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1986. Min Act: -0.1700
Data Index: 7960460 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1674. Min Act: -0.1700
Data Index: 4212469 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1361. Min Act: -0.1700
Data Index: 4887855 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1361. Min Act: -0.1700
Data Index: 3578057 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1361. Min Act: -0.1700
Data Index: 1558836 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1361. Min Act: -0.1700
Data Index: 7427919 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0736. Min Act: -0.1700
Data Index: 7006143 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0424. Min Act: -0.1700
Data Index: 1209675 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0736. Min Act: -0.1700
Data Index: 367518 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0424. Min Act: -0.1700
Data Index: 3420525 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 6379534 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 2742085 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9486. Min Act: -0.1700
Data Index: 6245814 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 1934109 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0111. Min Act: -0.1700
Data Index: 8749559 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9486. Min Act: -0.1700
Data Index: 2470237 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 5583513 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9486. Min Act: -0.1700
Data Index: 8096991 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9486. Min Act: -0.1700
Data Index: 1518068 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19