Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1079 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3492. Min Range: -7.3492
Max Act: 7.3492. Min Act: -0.1700
Data Index: 2576767 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3492. Min Range: -7.3492
Max Act: 7.1930. Min Act: -0.1700
Data Index: 1361176 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.9430. Min Act: -0.1700
Data Index: 2687246 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.9117. Min Act: -0.1700
Data Index: 8622800 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.7242. Min Act: -0.1700
Data Index: 1270180 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6617. Min Act: -0.1700
Data Index: 6612627 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6617. Min Act: -0.1700
Data Index: 6781460 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6305. Min Act: -0.1700
Data Index: 915318 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5992. Min Act: -0.1700
Data Index: 1042334 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5680. Min Act: -0.1700
Data Index: 915319 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5367. Min Act: -0.1700
Data Index: 6895520 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5367. Min Act: -0.1700
Data Index: 3574298 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5367. Min Act: -0.1700
Data Index: 8232807 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.4742. Min Act: -0.1700
Data Index: 8532785 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5367. Min Act: -0.1700
Data Index: 1716946 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5367. Min Act: -0.1700
Data Index: 1843826 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.4742. Min Act: -0.1700
Data Index: 3681324 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.4742. Min Act: -0.1700
Data Index: 6151479 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.4742. Min Act: -0.1700
Data Index: 8488202 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.4742. Min Act: -0.1700
Data Index: 8342500 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19