Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.9343. Min Act: -0.1700
Data Index: 6565728 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.8093. Min Act: -0.1700
Data Index: 7673353 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.8093. Min Act: -0.1700
Data Index: 4985942 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.6531. Min Act: -0.1700
Data Index: 1928889 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.6843. Min Act: -0.1700
Data Index: 5476267 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.6218. Min Act: -0.1700
Data Index: 5901455 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.5281. Min Act: -0.1700
Data Index: 820354 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.4656. Min Act: -0.1700
Data Index: 312343 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.4656. Min Act: -0.1700
Data Index: 6973700 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.4656. Min Act: -0.1700
Data Index: 5745295 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.4031. Min Act: -0.1700
Data Index: 5794088 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.4031. Min Act: -0.1700
Data Index: 3854248 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.4031. Min Act: -0.1700
Data Index: 3309369 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.4031. Min Act: -0.1700
Data Index: 2010366 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.3406. Min Act: -0.1700
Data Index: 5883788 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.3718. Min Act: -0.1700
Data Index: 5254132 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.3406. Min Act: -0.1700
Data Index: 1991828 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.3093. Min Act: -0.1700
Data Index: 4736631 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.3406. Min Act: -0.1700
Data Index: 643119 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9343. Min Range: -7.9343
Max Act: 7.3406. Min Act: -0.1700
Data Index: 1022680 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19