Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4818. Min Range: -9.4818
Max Act: 9.4818. Min Act: -0.1700
Data Index: 2115975 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.7943. Min Act: -0.1700
Data Index: 8352913 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.6693. Min Act: -0.1700
Data Index: 5338924 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.4193. Min Act: -0.1700
Data Index: 1398561 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.3568. Min Act: -0.1700
Data Index: 820712 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.3568. Min Act: -0.1700
Data Index: 8607664 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.3568. Min Act: -0.1700
Data Index: 1786006 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.3568. Min Act: -0.1700
Data Index: 4408195 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.2318. Min Act: -0.1700
Data Index: 8544239 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.2318. Min Act: -0.1700
Data Index: 7513717 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.2318. Min Act: -0.1700
Data Index: 6745451 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.1693. Min Act: -0.1700
Data Index: 4288689 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.1068. Min Act: -0.1700
Data Index: 1744294 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.1068. Min Act: -0.1700
Data Index: 885001 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.1693. Min Act: -0.1700
Data Index: 6165241 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.1068. Min Act: -0.1700
Data Index: 6870240 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.0443. Min Act: -0.1700
Data Index: 6815336 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.0443. Min Act: -0.1700
Data Index: 1438701 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4818. Min Range: -9.4818
Max Act: 7.9818. Min Act: -0.1700
Data Index: 5306420 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4818. Min Range: -9.4818
Max Act: 8.0443. Min Act: -0.1700
Data Index: 7480629 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19