Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9847. Min Act: -0.1700
Data Index: 5213776 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9535. Min Act: -0.1698
Data Index: 4626908 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9535. Min Act: -0.1700
Data Index: 2729864 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9535. Min Act: -0.1699
Data Index: 8601965 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9222. Min Act: -0.1698
Data Index: 3167612 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9535. Min Act: -0.1700
Data Index: 4100948 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9222. Min Act: -0.1700
Data Index: 7241333 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.9222. Min Act: -0.1700
Data Index: 3009607 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 5079530 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 3554150 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 4476429 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 475156 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 7407481 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1652
Data Index: 6637104 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 6017978 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 5360204 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8910. Min Act: -0.1700
Data Index: 384030 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8597. Min Act: -0.1699
Data Index: 4558436 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8597. Min Act: -0.1700
Data Index: 3681332 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9847. Min Range: -5.9847
Max Act: 5.8597. Min Act: -0.1700
Data Index: 5010047 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19