Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1628 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.8921. Min Act: -0.1700
Data Index: 8748791 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.7358. Min Act: -0.1700
Data Index: 5816903 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.6421. Min Act: -0.1700
Data Index: 2959633 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.4546. Min Act: -0.1700
Data Index: 5926698 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.3921. Min Act: -0.1700
Data Index: 5926697 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.3608. Min Act: -0.1700
Data Index: 5978498 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.2983. Min Act: -0.1700
Data Index: 2771726 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.2671. Min Act: -0.1700
Data Index: 6700210 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.2358. Min Act: -0.1700
Data Index: 6700209 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.2046. Min Act: -0.1700
Data Index: 4629550 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.2046. Min Act: -0.1700
Data Index: 1262627 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.1733. Min Act: -0.1700
Data Index: 2403848 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.1733. Min Act: -0.1700
Data Index: 6530702 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.0796. Min Act: -0.1700
Data Index: 5945519 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.0796. Min Act: -0.1700
Data Index: 8435363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.0796. Min Act: -0.1700
Data Index: 3044920 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.0483. Min Act: -0.1700
Data Index: 6686478 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.0483. Min Act: -0.1700
Data Index: 2541922 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.0483. Min Act: -0.1700
Data Index: 7444473 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8921. Min Range: -5.8921
Max Act: 5.0483. Min Act: -0.1700
Data Index: 7822511 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19