Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5406 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.9233. Min Act: -0.1700
Data Index: 5841657 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.6421. Min Act: -0.1700
Data Index: 3028876 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.6733. Min Act: -0.1700
Data Index: 2164010 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.5483. Min Act: -0.1700
Data Index: 2330841 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.4858. Min Act: -0.1700
Data Index: 3856633 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.4233. Min Act: -0.1700
Data Index: 1079655 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.3608. Min Act: -0.1700
Data Index: 5512304 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.3608. Min Act: -0.1700
Data Index: 3806148 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.3296. Min Act: -0.1700
Data Index: 741701 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2983. Min Act: -0.1700
Data Index: 3155570 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2983. Min Act: -0.1700
Data Index: 2505163 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2671. Min Act: -0.1700
Data Index: 1070420 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2671. Min Act: -0.1700
Data Index: 8691996 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2671. Min Act: -0.1700
Data Index: 7512909 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2671. Min Act: -0.1700
Data Index: 2941582 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2671. Min Act: -0.1700
Data Index: 6886366 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2671. Min Act: -0.1700
Data Index: 6815536 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2671. Min Act: -0.1700
Data Index: 3289111 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2358. Min Act: -0.1700
Data Index: 3761846 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9233. Min Range: -6.9233
Max Act: 6.2358. Min Act: -0.1700
Data Index: 2335434 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19