Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1963 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3029. Min Range: -6.3029
Max Act: 6.3029. Min Act: -0.1700
Data Index: 823416 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3029. Min Range: -6.3029
Max Act: 6.2404. Min Act: -0.1700
Data Index: 2976776 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3029. Min Range: -6.3029
Max Act: 6.1467. Min Act: -0.1700
Data Index: 8130663 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3029. Min Range: -6.3029
Max Act: 6.0217. Min Act: -0.1700
Data Index: 6002890 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.9592. Min Act: -0.1700
Data Index: 6200898 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.8967. Min Act: -0.1700
Data Index: 3192446 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.8342. Min Act: -0.1700
Data Index: 5335148 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.8654. Min Act: -0.1700
Data Index: 4842814 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.8342. Min Act: -0.1700
Data Index: 3214610 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.8029. Min Act: -0.1700
Data Index: 4378217 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7404. Min Act: -0.1700
Data Index: 3152932 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7717. Min Act: -0.1700
Data Index: 1958831 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7717. Min Act: -0.1700
Data Index: 2493082 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7717. Min Act: -0.1700
Data Index: 6758702 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7404. Min Act: -0.1700
Data Index: 5065657 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7404. Min Act: -0.1700
Data Index: 8202284 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7092. Min Act: -0.1700
Data Index: 4876066 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7092. Min Act: -0.1700
Data Index: 1611668 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7092. Min Act: -0.1700
Data Index: 7456461 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3029. Min Range: -6.3029
Max Act: 5.7092. Min Act: -0.1700
Data Index: 1898948 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19