Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 209 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0459. Min Range: -10.0459
Max Act: 10.0459. Min Act: -0.1700
Data Index: 6241477 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.2959. Min Act: -0.1700
Data Index: 4206615 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.2959. Min Act: -0.1700
Data Index: 3168880 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.2334. Min Act: -0.1700
Data Index: 2208344 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.1084. Min Act: -0.1700
Data Index: 6949812 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.1084. Min Act: -0.1700
Data Index: 6252060 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.0459. Min Act: -0.1700
Data Index: 7367413 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.1084. Min Act: -0.1700
Data Index: 7349767 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.0459. Min Act: -0.1700
Data Index: 8531466 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.0459. Min Act: -0.1700
Data Index: 5554004 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9834. Min Act: -0.1700
Data Index: 3465941 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9209. Min Act: -0.1700
Data Index: 1278654 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9834. Min Act: -0.1700
Data Index: 8742153 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9834. Min Act: -0.1700
Data Index: 4828936 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0459. Min Range: -10.0459
Max Act: 9.0459. Min Act: -0.1700
Data Index: 2627527 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9834. Min Act: -0.1700
Data Index: 420164 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9834. Min Act: -0.1700
Data Index: 173672 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9209. Min Act: -0.1700
Data Index: 1802806 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9209. Min Act: -0.1700
Data Index: 7110497 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0459. Min Range: -10.0459
Max Act: 8.9209. Min Act: -0.1700
Data Index: 4565914 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19