Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.2056. Min Act: -0.1700
Data Index: 450805 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.2056. Min Act: -0.1700
Data Index: 8577100 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.1430. Min Act: -0.1700
Data Index: 1419650 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.1430. Min Act: -0.1700
Data Index: 118627 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.1118. Min Act: -0.1700
Data Index: 4839823 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 8060582 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.1118. Min Act: -0.1700
Data Index: 5779393 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.1118. Min Act: -0.1700
Data Index: 4513433 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 4017520 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0493. Min Act: -0.1700
Data Index: 1846110 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 2763139 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 4553997 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0493. Min Act: -0.1700
Data Index: 2407116 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 4367827 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.1118. Min Act: -0.1700
Data Index: 4671141 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 7574401 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 3906807 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 3437646 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 5847256 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2056. Min Range: -4.2056
Max Act: 4.0805. Min Act: -0.1700
Data Index: 2093768 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19