Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9974. Min Act: -0.1696
Data Index: 7028327 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9974. Min Act: -0.1700
Data Index: 5714214 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9658. Min Act: -0.1700
Data Index: 3401967 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9658. Min Act: -0.1700
Data Index: 5058682 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9499. Min Act: -0.1671
Data Index: 7028322 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9341. Min Act: -0.1700
Data Index: 8188890 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9341. Min Act: -0.1700
Data Index: 7919948 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9341. Min Act: -0.1689
Data Index: 7028326 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9183. Min Act: -0.1700
Data Index: 7646837 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9183. Min Act: -0.1700
Data Index: 337351 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9183. Min Act: -0.1686
Data Index: 4477752 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9024. Min Act: -0.1700
Data Index: 7068426 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9024. Min Act: -0.1649
Data Index: 4477754 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9024. Min Act: -0.1700
Data Index: 5158133 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.9024. Min Act: -0.1700
Data Index: 2150797 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.8865. Min Act: -0.1700
Data Index: 953378 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.8707. Min Act: -0.1700
Data Index: 4808101 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.8865. Min Act: -0.1700
Data Index: 5617673 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.8865. Min Act: -0.1700
Data Index: 8003656 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9974. Min Range: -2.9974
Max Act: 2.8865. Min Act: -0.1700
Data Index: 844721 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19