Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1720 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.2870. Min Act: -0.1700
Data Index: 1313111 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1928. Min Act: -0.1700
Data Index: 4067415 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1928. Min Act: -0.1700
Data Index: 5580441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1613. Min Act: -0.1700
Data Index: 1590431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1613. Min Act: -0.1700
Data Index: 4250164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1613. Min Act: -0.1700
Data Index: 7721539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.0983. Min Act: -0.1700
Data Index: 2576552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 8701821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 14548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 8103551 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 1207844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 8017750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 6081868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 4957094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 3677249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 1999945 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1613. Min Act: -0.1700
Data Index: 3514667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 3293446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.1298. Min Act: -0.1700
Data Index: 3242989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2870. Min Range: -3.2870
Max Act: 3.0983. Min Act: -0.1700
Data Index: 2164710 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19