Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2332. Min Range: -9.2332
Max Act: 9.2332. Min Act: -0.1700
Data Index: 631046 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.7957. Min Act: -0.1700
Data Index: 1969069 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.6707. Min Act: -0.1700
Data Index: 4950666 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.5457. Min Act: -0.1700
Data Index: 4124264 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.4832. Min Act: -0.1700
Data Index: 8487255 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.4832. Min Act: -0.1700
Data Index: 6753313 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.4207. Min Act: -0.1700
Data Index: 7609894 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.4832. Min Act: -0.1700
Data Index: 23037 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.4832. Min Act: -0.1700
Data Index: 8298512 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.3582. Min Act: -0.1700
Data Index: 5840817 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2957. Min Act: -0.1700
Data Index: 7507192 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2957. Min Act: -0.1700
Data Index: 4221882 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2957. Min Act: -0.1700
Data Index: 4849863 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2957. Min Act: -0.1700
Data Index: 1038830 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2957. Min Act: -0.1700
Data Index: 8309583 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2957. Min Act: -0.1700
Data Index: 7702016 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2332. Min Act: -0.1700
Data Index: 3399291 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.1707. Min Act: -0.1700
Data Index: 5352628 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2332. Min Act: -0.1700
Data Index: 8398764 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2332. Min Range: -9.2332
Max Act: 8.2332. Min Act: -0.1700
Data Index: 6416992 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19