Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6160 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.6933. Min Act: -0.1700
Data Index: 7814341 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.6621. Min Act: -0.1700
Data Index: 8475966 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.6621. Min Act: -0.1700
Data Index: 2141705 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.5996. Min Act: -0.1700
Data Index: 8274636 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.5996. Min Act: -0.1700
Data Index: 7164224 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.5058. Min Act: -0.1700
Data Index: 815427 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.5058. Min Act: -0.1700
Data Index: 1310720 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.4746. Min Act: -0.1700
Data Index: 2820574 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.4746. Min Act: -0.1700
Data Index: 5059036 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.4433. Min Act: -0.1700
Data Index: 1638566 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.3808. Min Act: -0.1700
Data Index: 6618286 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.3496. Min Act: -0.1700
Data Index: 5511936 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.3496. Min Act: -0.1700
Data Index: 948303 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.3183. Min Act: -0.1700
Data Index: 5719544 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.2871. Min Act: -0.1700
Data Index: 5678710 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.2871. Min Act: -0.1700
Data Index: 1443121 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.2871. Min Act: -0.1700
Data Index: 1393635 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.2871. Min Act: -0.1700
Data Index: 1477283 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.2558. Min Act: -0.1700
Data Index: 1097572 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6933. Min Range: -7.6933
Max Act: 7.2246. Min Act: -0.1700
Data Index: 4753018 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19