Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5446 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.6053. Min Act: -0.1700
Data Index: 5734463 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.5116. Min Act: -0.1700
Data Index: 8230940 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.4178. Min Act: -0.1700
Data Index: 4815667 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.4178. Min Act: -0.1700
Data Index: 6751610 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.3866. Min Act: -0.1700
Data Index: 1612766 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.3866. Min Act: -0.1700
Data Index: 1666624 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.3241. Min Act: -0.1700
Data Index: 5675478 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.2616. Min Act: -0.1700
Data Index: 6802483 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.2928. Min Act: -0.1700
Data Index: 21909 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.3241. Min Act: -0.1700
Data Index: 6900140 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.2928. Min Act: -0.1700
Data Index: 4230349 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.2616. Min Act: -0.1700
Data Index: 3310040 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.2616. Min Act: -0.1700
Data Index: 8163957 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.2303. Min Act: -0.1700
Data Index: 2686461 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.1991. Min Act: -0.1700
Data Index: 7442305 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.1991. Min Act: -0.1700
Data Index: 1516501 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.1991. Min Act: -0.1699
Data Index: 1654908 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.1991. Min Act: -0.1700
Data Index: 6989680 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.1991. Min Act: -0.1700
Data Index: 259457 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6053. Min Range: -6.6053
Max Act: 6.1678. Min Act: -0.1700
Data Index: 2555917 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19