Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0439. Min Range: -5.0439
Max Act: 5.0439. Min Act: -0.1700
Data Index: 7398180 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6689. Min Act: -0.1700
Data Index: 7293082 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6689. Min Act: -0.1700
Data Index: 7674709 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6689. Min Act: -0.1700
Data Index: 2026253 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6377. Min Act: -0.1700
Data Index: 5987241 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6377. Min Act: -0.1700
Data Index: 7161645 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6064. Min Act: -0.1700
Data Index: 7112013 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6064. Min Act: -0.1700
Data Index: 1142244 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6064. Min Act: -0.1700
Data Index: 2317107 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6064. Min Act: -0.1700
Data Index: 5505917 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.6064. Min Act: -0.1700
Data Index: 1145657 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.5752. Min Act: -0.1700
Data Index: 3434258 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.5752. Min Act: -0.1700
Data Index: 4254385 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.5752. Min Act: -0.1700
Data Index: 2058930 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.5752. Min Act: -0.1700
Data Index: 5893581 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.5127. Min Act: -0.1700
Data Index: 5923076 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.5127. Min Act: -0.1699
Data Index: 2778086 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.4814. Min Act: -0.1700
Data Index: 3227894 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.4814. Min Act: -0.1700
Data Index: 4451028 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.4814. Min Act: -0.1700
Data Index: 5971213 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19