Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5870 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.3387. Min Act: -0.1700
Data Index: 2899229 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.2762. Min Act: -0.1700
Data Index: 6166186 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.0887. Min Act: -0.1700
Data Index: 6215502 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.0887. Min Act: -0.1700
Data Index: 2899218 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.1200. Min Act: -0.1700
Data Index: 6566408 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.0575. Min Act: -0.1700
Data Index: 957862 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.0575. Min Act: -0.1700
Data Index: 2690479 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3387. Min Range: -7.3387
Max Act: 7.0262. Min Act: -0.1700
Data Index: 2775416 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.9637. Min Act: -0.1700
Data Index: 7309059 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.9637. Min Act: -0.1700
Data Index: 4022311 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.9325. Min Act: -0.1700
Data Index: 8686654 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.9012. Min Act: -0.1700
Data Index: 4620587 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8700. Min Act: -0.1700
Data Index: 7382233 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8700. Min Act: -0.1700
Data Index: 3729103 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8700. Min Act: -0.1700
Data Index: 4142034 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8700. Min Act: -0.1700
Data Index: 4406596 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8387. Min Act: -0.1700
Data Index: 6819770 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8075. Min Act: -0.1700
Data Index: 5175120 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8075. Min Act: -0.1700
Data Index: 5492244 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3387. Min Range: -7.3387
Max Act: 6.8075. Min Act: -0.1700
Data Index: 3289405 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19