Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4963. Min Range: -8.4963
Max Act: 8.4963. Min Act: -0.1700
Data Index: 4158607 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4963. Min Range: -8.4963
Max Act: 8.2463. Min Act: -0.1700
Data Index: 2886830 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4963. Min Range: -8.4963
Max Act: 8.1838. Min Act: -0.1700
Data Index: 870017 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4963. Min Range: -8.4963
Max Act: 8.1213. Min Act: -0.1700
Data Index: 870018 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4963. Min Range: -8.4963
Max Act: 8.0588. Min Act: -0.1700
Data Index: 6878793 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.9963. Min Act: -0.1700
Data Index: 323826 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.9963. Min Act: -0.1700
Data Index: 8422564 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.9963. Min Act: -0.1700
Data Index: 1469836 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.9338. Min Act: -0.1700
Data Index: 3717499 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.9963. Min Act: -0.1700
Data Index: 4251187 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8713. Min Act: -0.1700
Data Index: 7473374 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8713. Min Act: -0.1700
Data Index: 6926684 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8713. Min Act: -0.1700
Data Index: 1729768 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8713. Min Act: -0.1700
Data Index: 6863884 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8713. Min Act: -0.1700
Data Index: 4565523 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8713. Min Act: -0.1700
Data Index: 3536936 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8401. Min Act: -0.1700
Data Index: 1637699 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8401. Min Act: -0.1700
Data Index: 1469834 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8401. Min Act: -0.1700
Data Index: 8298528 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4963. Min Range: -8.4963
Max Act: 7.8088. Min Act: -0.1700
Data Index: 8259682 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19