Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0792. Min Range: -6.0792
Max Act: 6.0792. Min Act: -0.1700
Data Index: 977165 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0792. Min Range: -6.0792
Max Act: 6.0792. Min Act: -0.1700
Data Index: 1132193 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0792. Min Range: -6.0792
Max Act: 6.0167. Min Act: -0.1700
Data Index: 6850592 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.9230. Min Act: -0.1700
Data Index: 7346658 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.8917. Min Act: -0.1700
Data Index: 720987 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2504714 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.8605. Min Act: -0.1700
Data Index: 3375305 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2157855 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.8292. Min Act: -0.1700
Data Index: 8557329 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.7355. Min Act: -0.1700
Data Index: 437696 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.7355. Min Act: -0.1700
Data Index: 7777546 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.7042. Min Act: -0.1700
Data Index: 4343863 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 2145953 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 7955897 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 6230915 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 2651083 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 1072963 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 4790837 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 2260459 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0792. Min Range: -6.0792
Max Act: 5.6730. Min Act: -0.1700
Data Index: 8238052 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19