Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.7131. Min Act: -0.1700
Data Index: 7226637 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 7125474 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4318. Min Act: -0.1700
Data Index: 6911705 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4318. Min Act: -0.1700
Data Index: 6421240 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4318. Min Act: -0.1700
Data Index: 985969 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3693. Min Act: -0.1700
Data Index: 6998297 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4006. Min Act: -0.1700
Data Index: 2553137 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3693. Min Act: -0.1700
Data Index: 3958616 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3068. Min Act: -0.1700
Data Index: 4618730 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2756. Min Act: -0.1700
Data Index: 660723 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2756. Min Act: -0.1700
Data Index: 478796 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3068. Min Act: -0.1700
Data Index: 2815419 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 56310 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 637936 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 1437136 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 7533049 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 5329088 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 4865691 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 270527 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1193. Min Act: -0.1700
Data Index: 1180831 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19