Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1596 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0301. Min Range: -5.0301
Max Act: 5.0301. Min Act: -0.1700
Data Index: 8127921 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9989. Min Act: -0.1700
Data Index: 5372090 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9676. Min Act: -0.1700
Data Index: 1601666 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9989. Min Act: -0.1700
Data Index: 1138076 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9364. Min Act: -0.1700
Data Index: 8828081 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9364. Min Act: -0.1700
Data Index: 4530875 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 6706743 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 2753597 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 3308843 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.9051. Min Act: -0.1700
Data Index: 2753594 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8739. Min Act: -0.1700
Data Index: 2761223 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2769893 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2753593 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8739. Min Act: -0.1700
Data Index: 5336685 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 150583 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 7320586 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 7320585 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 4051439 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 3168672 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0301. Min Range: -5.0301
Max Act: 4.8426. Min Act: -0.1700
Data Index: 2753598 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19