Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 605 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.9804. Min Act: -0.1700
Data Index: 8353031 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.9492. Min Act: -0.1700
Data Index: 76359 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.9804. Min Act: -0.1700
Data Index: 3608662 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.9179. Min Act: -0.1700
Data Index: 4925777 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.9179. Min Act: -0.1699
Data Index: 2080150 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8867. Min Act: -0.1700
Data Index: 5780723 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.9179. Min Act: -0.1700
Data Index: 6264328 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.9492. Min Act: -0.1700
Data Index: 1731812 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8867. Min Act: -0.1700
Data Index: 6187633 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8867. Min Act: -0.1700
Data Index: 3960685 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8867. Min Act: -0.1700
Data Index: 5696012 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8554. Min Act: -0.1700
Data Index: 2069072 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8554. Min Act: -0.1700
Data Index: 274695 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8554. Min Act: -0.1700
Data Index: 174542 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8554. Min Act: -0.1700
Data Index: 1387381 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8242. Min Act: -0.1700
Data Index: 5604638 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.8554. Min Act: -0.1699
Data Index: 7019881 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.7929. Min Act: -0.1700
Data Index: 7043770 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.7929. Min Act: -0.1700
Data Index: 5098512 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9804. Min Range: -4.9804
Max Act: 4.7929. Min Act: -0.1700
Data Index: 5640233 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19