Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.2028. Min Act: -0.1700
Data Index: 346775 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.1241. Min Act: -0.1700
Data Index: 6714079 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.0926. Min Act: -0.1700
Data Index: 3175798 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.1083. Min Act: -0.1700
Data Index: 3740031 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.0926. Min Act: -0.1700
Data Index: 2287925 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.0610. Min Act: -0.1700
Data Index: 2061993 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.0610. Min Act: -0.1700
Data Index: 748843 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.0295. Min Act: -0.1700
Data Index: 2282164 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.0295. Min Act: -0.1700
Data Index: 1679933 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9979. Min Act: -0.1700
Data Index: 1328519 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9979. Min Act: -0.1700
Data Index: 3976670 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9979. Min Act: -0.1700
Data Index: 7048575 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9821. Min Act: -0.1700
Data Index: 4334608 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2028. Min Range: -3.2028
Max Act: 3.0137. Min Act: -0.1700
Data Index: 2451956 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9821. Min Act: -0.1700
Data Index: 3453000 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9821. Min Act: -0.1700
Data Index: 4729929 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9662. Min Act: -0.1700
Data Index: 8459834 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9504. Min Act: -0.1700
Data Index: 3811365 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9662. Min Act: -0.1700
Data Index: 2807674 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2028. Min Range: -3.2028
Max Act: 2.9346. Min Act: -0.1700
Data Index: 407092 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19