Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.3618. Min Act: -0.1700
Data Index: 2479331 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.2055. Min Act: -0.1700
Data Index: 4146184 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.2055. Min Act: -0.1700
Data Index: 4414762 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1743. Min Act: -0.1700
Data Index: 1849340 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1743. Min Act: -0.1700
Data Index: 2395686 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1743. Min Act: -0.1700
Data Index: 659518 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1430. Min Act: -0.1700
Data Index: 714360 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1430. Min Act: -0.1700
Data Index: 4538622 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1430. Min Act: -0.1700
Data Index: 230926 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1743. Min Act: -0.1700
Data Index: 82061 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1430. Min Act: -0.1700
Data Index: 5326907 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.1118. Min Act: -0.1700
Data Index: 5494192 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0805. Min Act: -0.1700
Data Index: 908232 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0805. Min Act: -0.1700
Data Index: 487404 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0805. Min Act: -0.1700
Data Index: 1690287 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0805. Min Act: -0.1700
Data Index: 7559599 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0180. Min Act: -0.1700
Data Index: 1546593 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0180. Min Act: -0.1700
Data Index: 1143965 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0493. Min Act: -0.1700
Data Index: 2999882 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3618. Min Range: -4.3618
Max Act: 4.0493. Min Act: -0.1700
Data Index: 5087592 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19