Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.5392. Min Act: -0.1700
Data Index: 5804763 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.4454. Min Act: -0.1700
Data Index: 2243385 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.4142. Min Act: -0.1700
Data Index: 5948077 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.3829. Min Act: -0.1700
Data Index: 5345307 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.3829. Min Act: -0.1700
Data Index: 5059326 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.3829. Min Act: -0.1700
Data Index: 4877060 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.3517. Min Act: -0.1700
Data Index: 6012142 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.3517. Min Act: -0.1700
Data Index: 4775965 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.3517. Min Act: -0.1700
Data Index: 1595626 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.3204. Min Act: -0.1700
Data Index: 2199561 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.2892. Min Act: -0.1700
Data Index: 8636513 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.2579. Min Act: -0.1700
Data Index: 5948074 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.2579. Min Act: -0.1700
Data Index: 3142524 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.2579. Min Act: -0.1700
Data Index: 7256651 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.2579. Min Act: -0.1700
Data Index: 5018198 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.2267. Min Act: -0.1700
Data Index: 2773772 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.1954. Min Act: -0.1700
Data Index: 3161523 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.1954. Min Act: -0.1700
Data Index: 7843976 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.1954. Min Act: -0.1700
Data Index: 5985754 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5392. Min Range: -5.5392
Max Act: 5.1329. Min Act: -0.1699
Data Index: 7843984 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19