Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4803 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.7810. Min Act: -0.1700
Data Index: 7351683 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.7184. Min Act: -0.1700
Data Index: 8379674 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.7184. Min Act: -0.1700
Data Index: 6790009 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.5932. Min Act: -0.1700
Data Index: 3503157 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.5776. Min Act: -0.1700
Data Index: 531336 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.5776. Min Act: -0.1700
Data Index: 7176958 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.5463. Min Act: -0.1700
Data Index: 769980 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.5306. Min Act: -0.1700
Data Index: 3194800 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4993. Min Act: -0.1700
Data Index: 1523887 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4993. Min Act: -0.1700
Data Index: 6329774 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4680. Min Act: -0.1700
Data Index: 2616296 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4523. Min Act: -0.1700
Data Index: 5536119 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4523. Min Act: -0.1700
Data Index: 5918769 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4523. Min Act: -0.1700
Data Index: 7509117 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4366. Min Act: -0.1700
Data Index: 4006863 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4523. Min Act: -0.1700
Data Index: 5678742 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4053. Min Act: -0.1700
Data Index: 936536 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.4053. Min Act: -0.1700
Data Index: 8508035 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.3896. Min Act: -0.1700
Data Index: 5668929 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7810. Min Range: -3.7810
Max Act: 3.3739. Min Act: -0.1700
Data Index: 3400604 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19