Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.8959. Min Act: -0.1700
Data Index: 3728488 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.7084. Min Act: -0.1700
Data Index: 7474669 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.5834. Min Act: -0.1700
Data Index: 5266667 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.5209. Min Act: -0.1700
Data Index: 6531577 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.4584. Min Act: -0.1700
Data Index: 6797582 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.3959. Min Act: -0.1700
Data Index: 3664193 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.4272. Min Act: -0.1700
Data Index: 653100 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.3959. Min Act: -0.1700
Data Index: 5341356 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1719683 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.3022. Min Act: -0.1700
Data Index: 1455062 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.2709. Min Act: -0.1700
Data Index: 6505459 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.3022. Min Act: -0.1700
Data Index: 8160230 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.2709. Min Act: -0.1700
Data Index: 4944495 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3697037 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.1772. Min Act: -0.1700
Data Index: 2524236 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.2084. Min Act: -0.1700
Data Index: 2020359 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.1772. Min Act: -0.1700
Data Index: 7028514 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.1772. Min Act: -0.1700
Data Index: 1318527 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.1772. Min Act: -0.1700
Data Index: 7899029 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8959. Min Range: -6.8959
Max Act: 6.1459. Min Act: -0.1700
Data Index: 5711526 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19