Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.4190. Min Act: -0.1700
Data Index: 2771295 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.4190. Min Act: -0.1700
Data Index: 1271361 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.2940. Min Act: -0.1700
Data Index: 5653922 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.2940. Min Act: -0.1700
Data Index: 8587670 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.2315. Min Act: -0.1700
Data Index: 4583661 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.2315. Min Act: -0.1700
Data Index: 2871733 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1690. Min Act: -0.1700
Data Index: 7847820 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1690. Min Act: -0.1700
Data Index: 7892576 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1690. Min Act: -0.1700
Data Index: 128173 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1690. Min Act: -0.1700
Data Index: 2607234 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1065. Min Act: -0.1700
Data Index: 3779577 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1065. Min Act: -0.1700
Data Index: 1311697 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1065. Min Act: -0.1700
Data Index: 3742724 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.1065. Min Act: -0.1700
Data Index: 7578206 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.0440. Min Act: -0.1700
Data Index: 3988678 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.0440. Min Act: -0.1700
Data Index: 2331795 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.0440. Min Act: -0.1700
Data Index: 6564360 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.0440. Min Act: -0.1700
Data Index: 5464451 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4190. Min Range: -8.4190
Max Act: 8.0440. Min Act: -0.1700
Data Index: 7443564 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4190. Min Range: -8.4190
Max Act: 7.9190. Min Act: -0.1700
Data Index: 7345742 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19