Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4959. Min Range: -7.4959
Max Act: 7.4959. Min Act: -0.1700
Data Index: 5250410 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.9959. Min Act: -0.1700
Data Index: 6651929 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.9647. Min Act: -0.1700
Data Index: 7132569 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.8709. Min Act: -0.1700
Data Index: 7936169 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.8397. Min Act: -0.1700
Data Index: 8599258 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.8709. Min Act: -0.1700
Data Index: 7975356 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.8084. Min Act: -0.1700
Data Index: 4637305 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.7772. Min Act: -0.1700
Data Index: 2098284 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.7772. Min Act: -0.1700
Data Index: 3090301 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.7459. Min Act: -0.1700
Data Index: 8633976 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.6834. Min Act: -0.1700
Data Index: 6568703 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.7147. Min Act: -0.1700
Data Index: 5631778 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.7147. Min Act: -0.1700
Data Index: 775781 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.7147. Min Act: -0.1700
Data Index: 7309350 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.6522. Min Act: -0.1700
Data Index: 3147388 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.6834. Min Act: -0.1700
Data Index: 1451983 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.7147. Min Act: -0.1700
Data Index: 277926 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.6522. Min Act: -0.1700
Data Index: 3255285 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.6209. Min Act: -0.1700
Data Index: 225858 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4959. Min Range: -7.4959
Max Act: 6.6209. Min Act: -0.1700
Data Index: 2343145 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19