Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3317 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.3808. Min Act: -0.1700
Data Index: 8618454 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.3496. Min Act: -0.1700
Data Index: 8071980 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.2558. Min Act: -0.1700
Data Index: 52443 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.2246. Min Act: -0.1700
Data Index: 5217047 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.1933. Min Act: -0.1700
Data Index: 3546814 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.1933. Min Act: -0.1700
Data Index: 3951985 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.1933. Min Act: -0.1700
Data Index: 8043633 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.1621. Min Act: -0.1700
Data Index: 917971 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.1308. Min Act: -0.1700
Data Index: 1849228 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.1621. Min Act: -0.1700
Data Index: 2593200 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.1308. Min Act: -0.1700
Data Index: 3196977 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0683. Min Act: -0.1700
Data Index: 3682670 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0683. Min Act: -0.1700
Data Index: 5638045 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0371. Min Act: -0.1700
Data Index: 7580996 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0371. Min Act: -0.1700
Data Index: 4629098 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0371. Min Act: -0.1700
Data Index: 4629094 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0371. Min Act: -0.1700
Data Index: 6184947 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0058. Min Act: -0.1700
Data Index: 7227669 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0058. Min Act: -0.1700
Data Index: 6614711 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3808. Min Range: -5.3808
Max Act: 5.0058. Min Act: -0.1700
Data Index: 5642667 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19