Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.7433. Min Act: -0.1700
Data Index: 4597524 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.7433. Min Act: -0.1700
Data Index: 8422195 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 2585041 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 7719723 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.7121. Min Act: -0.1700
Data Index: 3140015 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.6808. Min Act: -0.1700
Data Index: 5850624 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.6496. Min Act: -0.1700
Data Index: 6713778 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.6183. Min Act: -0.1700
Data Index: 6713777 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.6496. Min Act: -0.1700
Data Index: 8489926 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.6496. Min Act: -0.1700
Data Index: 7414542 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.6496. Min Act: -0.1700
Data Index: 7171559 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.6496. Min Act: -0.1700
Data Index: 5801122 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5558. Min Act: -0.1700
Data Index: 3621600 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5871. Min Act: -0.1700
Data Index: 7657092 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5871. Min Act: -0.1700
Data Index: 2551178 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5558. Min Act: -0.1700
Data Index: 3875354 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5558. Min Act: -0.1700
Data Index: 7476701 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5558. Min Act: -0.1700
Data Index: 6103917 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5558. Min Act: -0.1700
Data Index: 46376 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7433. Min Range: -4.7433
Max Act: 4.5558. Min Act: -0.1700
Data Index: 659880 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19