Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.6804. Min Act: -0.1700
Data Index: 983513 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.6804. Min Act: -0.1700
Data Index: 931113 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.6804. Min Act: -0.1700
Data Index: 3166388 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.6804. Min Act: -0.1700
Data Index: 8333324 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.6179. Min Act: -0.1700
Data Index: 686063 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.6179. Min Act: -0.1700
Data Index: 2759551 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.6179. Min Act: -0.1700
Data Index: 549858 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5554. Min Act: -0.1700
Data Index: 8414907 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5554. Min Act: -0.1700
Data Index: 201621 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5554. Min Act: -0.1700
Data Index: 7296248 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5554. Min Act: -0.1700
Data Index: 4000832 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 6082236 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 6176941 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 2991291 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 7057345 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 1265013 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5554. Min Act: -0.1699
Data Index: 450600 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 1306118 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 644833 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6804. Min Range: -6.6804
Max Act: 6.5241. Min Act: -0.1700
Data Index: 7662173 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19