Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1639 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.6246. Min Act: -0.1700
Data Index: 199207 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.5621. Min Act: -0.1700
Data Index: 8419376 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.5308. Min Act: -0.1700
Data Index: 2515561 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.4683. Min Act: -0.1700
Data Index: 8419382 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.4996. Min Act: -0.1700
Data Index: 1665471 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.4058. Min Act: -0.1700
Data Index: 1178102 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3746. Min Act: -0.1700
Data Index: 3907475 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.4058. Min Act: -0.1700
Data Index: 4091265 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3746. Min Act: -0.1700
Data Index: 1281306 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3746. Min Act: -0.1700
Data Index: 2597273 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.4058. Min Act: -0.1700
Data Index: 1624315 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3433. Min Act: -0.1700
Data Index: 4241707 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3746. Min Act: -0.1700
Data Index: 115325 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3433. Min Act: -0.1700
Data Index: 6834911 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3121. Min Act: -0.1700
Data Index: 5935928 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3121. Min Act: -0.1700
Data Index: 5326114 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3121. Min Act: -0.1700
Data Index: 8419388 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.3121. Min Act: -0.1700
Data Index: 7870987 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.2808. Min Act: -0.1700
Data Index: 470551 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6246. Min Range: -5.6246
Max Act: 5.2496. Min Act: -0.1700
Data Index: 2433982 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19