Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1543 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2086. Min Range: -6.2086
Max Act: 6.2086. Min Act: -0.1700
Data Index: 8110091 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2086. Min Range: -6.2086
Max Act: 6.1148. Min Act: -0.1700
Data Index: 7003311 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2086. Min Range: -6.2086
Max Act: 6.0211. Min Act: -0.1700
Data Index: 3710470 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2086. Min Range: -6.2086
Max Act: 6.0211. Min Act: -0.1700
Data Index: 2335348 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2086. Min Range: -6.2086
Max Act: 6.0211. Min Act: -0.1700
Data Index: 4599740 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.9273. Min Act: -0.1700
Data Index: 7966035 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.9273. Min Act: -0.1700
Data Index: 924631 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.9273. Min Act: -0.1700
Data Index: 3733378 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.8961. Min Act: -0.1700
Data Index: 7954622 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.8961. Min Act: -0.1700
Data Index: 5348161 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.8648. Min Act: -0.1700
Data Index: 7574693 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.8336. Min Act: -0.1700
Data Index: 8361284 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.8336. Min Act: -0.1700
Data Index: 5613537 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.8023. Min Act: -0.1700
Data Index: 6013258 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.7398. Min Act: -0.1700
Data Index: 1710650 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.7398. Min Act: -0.1700
Data Index: 5163269 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.7398. Min Act: -0.1700
Data Index: 3359530 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.7711. Min Act: -0.1700
Data Index: 2194692 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.7398. Min Act: -0.1700
Data Index: 6243737 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2086. Min Range: -6.2086
Max Act: 5.6773. Min Act: -0.1700
Data Index: 1904763 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19