Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.7309. Min Act: -0.1700
Data Index: 97624 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6996. Min Act: -0.1700
Data Index: 2571518 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6370. Min Act: -0.1700
Data Index: 7362657 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6057. Min Act: -0.1700
Data Index: 482021 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6370. Min Act: -0.1700
Data Index: 6510072 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6370. Min Act: -0.1700
Data Index: 461854 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6370. Min Act: -0.1700
Data Index: 733985 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6057. Min Act: -0.1700
Data Index: 4281245 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.5744. Min Act: -0.1700
Data Index: 1654880 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6057. Min Act: -0.1700
Data Index: 7352503 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.5744. Min Act: -0.1700
Data Index: 5739565 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.6057. Min Act: -0.1700
Data Index: 3602406 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.5744. Min Act: -0.1700
Data Index: 4281246 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.5744. Min Act: -0.1700
Data Index: 2102392 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.5744. Min Act: -0.1700
Data Index: 6189920 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.4961. Min Act: -0.1700
Data Index: 1654879 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.4335. Min Act: -0.1700
Data Index: 1601471 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.4648. Min Act: -0.1700
Data Index: 5102927 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.3864. Min Act: -0.1700
Data Index: 7897604 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7309. Min Range: -3.7309
Max Act: 3.3080. Min Act: -0.1700
Data Index: 1983348 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19