Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.3214. Min Act: -0.1700
Data Index: 8604883 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.2586. Min Act: -0.1700
Data Index: 3812218 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.2114. Min Act: -0.1700
Data Index: 152654 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.2114. Min Act: -0.1700
Data Index: 4864500 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.2114. Min Act: -0.1700
Data Index: 560818 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.2114. Min Act: -0.1700
Data Index: 1048540 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.2114. Min Act: -0.1700
Data Index: 3863837 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1642. Min Act: -0.1700
Data Index: 3088005 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1642. Min Act: -0.1700
Data Index: 1106528 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1800. Min Act: -0.1700
Data Index: 6185003 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1642. Min Act: -0.1700
Data Index: 4220767 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1800. Min Act: -0.1700
Data Index: 4500584 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1485. Min Act: -0.1700
Data Index: 6329568 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1170. Min Act: -0.1700
Data Index: 3558939 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1642. Min Act: -0.1700
Data Index: 6567308 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1485. Min Act: -0.1700
Data Index: 5714833 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1485. Min Act: -0.1700
Data Index: 98986 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1485. Min Act: -0.1700
Data Index: 2404379 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1327. Min Act: -0.1700
Data Index: 6955973 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3214. Min Range: -3.3214
Max Act: 3.1642. Min Act: -0.1700
Data Index: 3018315 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19