Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1665 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.6391. Min Act: -0.1698
Data Index: 7984291 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.4204. Min Act: -0.1700
Data Index: 2791005 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.3891. Min Act: -0.1700
Data Index: 804155 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.3579. Min Act: -0.1699
Data Index: 4229591 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.3579. Min Act: -0.1700
Data Index: 4229579 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.2641. Min Act: -0.1700
Data Index: 1467438 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.2641. Min Act: -0.1700
Data Index: 2091680 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.1391. Min Act: -0.1700
Data Index: 4229593 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.1391. Min Act: -0.1700
Data Index: 4196234 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.1391. Min Act: -0.1700
Data Index: 7973465 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.1079. Min Act: -0.1700
Data Index: 518508 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.0766. Min Act: -0.1700
Data Index: 7875266 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.1079. Min Act: -0.1700
Data Index: 256818 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.0766. Min Act: -0.1700
Data Index: 7078500 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6391. Min Range: -7.6391
Max Act: 7.0141. Min Act: -0.1700
Data Index: 7857377 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6391. Min Range: -7.6391
Max Act: 6.9829. Min Act: -0.1700
Data Index: 8309169 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6391. Min Range: -7.6391
Max Act: 6.9829. Min Act: -0.1700
Data Index: 4229577 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6391. Min Range: -7.6391
Max Act: 6.9829. Min Act: -0.1700
Data Index: 4044804 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6391. Min Range: -7.6391
Max Act: 6.9516. Min Act: -0.1699
Data Index: 5238981 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6391. Min Range: -7.6391
Max Act: 6.9204. Min Act: -0.1700
Data Index: 5555034 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19