Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 784 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.5959. Min Act: -0.1700
Data Index: 1957403 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.5334. Min Act: -0.1700
Data Index: 384090 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.4709. Min Act: -0.1700
Data Index: 8271089 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.3771. Min Act: -0.1700
Data Index: 3365203 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.3771. Min Act: -0.1700
Data Index: 8302295 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.4084. Min Act: -0.1700
Data Index: 5769915 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.3459. Min Act: -0.1700
Data Index: 5379617 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.3459. Min Act: -0.1700
Data Index: 1534455 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2834. Min Act: -0.1700
Data Index: 5757100 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2209. Min Act: -0.1700
Data Index: 8369994 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2521. Min Act: -0.1700
Data Index: 8522930 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.1896. Min Act: -0.1700
Data Index: 7130247 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2209. Min Act: -0.1700
Data Index: 7628568 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2209. Min Act: -0.1700
Data Index: 719192 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2521. Min Act: -0.1700
Data Index: 4547081 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2209. Min Act: -0.1700
Data Index: 4419560 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.1896. Min Act: -0.1700
Data Index: 1716470 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.2209. Min Act: -0.1700
Data Index: 26048 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.1583. Min Act: -0.1700
Data Index: 7754226 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5959. Min Range: -4.5959
Max Act: 4.1583. Min Act: -0.1700
Data Index: 5060014 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19