Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.4720. Min Act: -0.1700
Data Index: 829522 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.4407. Min Act: -0.1700
Data Index: 7735787 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.3782. Min Act: -0.1700
Data Index: 2195866 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.3782. Min Act: -0.1700
Data Index: 7049571 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.3157. Min Act: -0.1700
Data Index: 4747875 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.3157. Min Act: -0.1700
Data Index: 978563 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2845. Min Act: -0.1700
Data Index: 7890232 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2532. Min Act: -0.1700
Data Index: 6429838 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2532. Min Act: -0.1700
Data Index: 6805065 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2532. Min Act: -0.1700
Data Index: 248756 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2220. Min Act: -0.1700
Data Index: 4448085 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2220. Min Act: -0.1700
Data Index: 4061762 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2220. Min Act: -0.1700
Data Index: 8764354 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2220. Min Act: -0.1700
Data Index: 1722208 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.2532. Min Act: -0.1700
Data Index: 4436403 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.1907. Min Act: -0.1700
Data Index: 2919424 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.1907. Min Act: -0.1700
Data Index: 748797 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.1907. Min Act: -0.1700
Data Index: 8497857 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.1907. Min Act: -0.1700
Data Index: 8282040 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4720. Min Range: -4.4720
Max Act: 4.1907. Min Act: -0.1700
Data Index: 4030022 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19