Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3506. Min Range: -7.3506
Max Act: 7.3506. Min Act: -0.1700
Data Index: 483690 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3506. Min Range: -7.3506
Max Act: 7.2256. Min Act: -0.1700
Data Index: 8280891 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3506. Min Range: -7.3506
Max Act: 7.1631. Min Act: -0.1700
Data Index: 1405859 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3506. Min Range: -7.3506
Max Act: 7.1006. Min Act: -0.1700
Data Index: 5992848 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3506. Min Range: -7.3506
Max Act: 7.0068. Min Act: -0.1700
Data Index: 3318571 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3506. Min Range: -7.3506
Max Act: 7.0068. Min Act: -0.1700
Data Index: 6777690 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.9756. Min Act: -0.1700
Data Index: 1989504 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.9443. Min Act: -0.1700
Data Index: 8753371 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8818. Min Act: -0.1700
Data Index: 2466975 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8818. Min Act: -0.1700
Data Index: 6797723 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8818. Min Act: -0.1700
Data Index: 8185839 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8818. Min Act: -0.1700
Data Index: 3459739 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 7888673 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 361998 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 4492031 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 8677169 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 483692 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 7769721 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8506. Min Act: -0.1700
Data Index: 7237446 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3506. Min Range: -7.3506
Max Act: 6.8818. Min Act: -0.1700
Data Index: 4925154 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19