Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.6616. Min Act: -0.1700
Data Index: 3973342 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.5991. Min Act: -0.1700
Data Index: 1759251 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.5366. Min Act: -0.1700
Data Index: 5717045 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.4429. Min Act: -0.1700
Data Index: 5429059 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.4429. Min Act: -0.1700
Data Index: 2996678 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.2554. Min Act: -0.1700
Data Index: 8661022 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.2241. Min Act: -0.1700
Data Index: 4049125 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.2241. Min Act: -0.1700
Data Index: 4671840 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 3898542 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 1534731 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 8179265 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0679. Min Act: -0.1700
Data Index: 2172150 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 8605211 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0679. Min Act: -0.1700
Data Index: 5804502 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0366. Min Act: -0.1700
Data Index: 5267476 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0366. Min Act: -0.1700
Data Index: 1741284 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0054. Min Act: -0.1700
Data Index: 7632935 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0366. Min Act: -0.1700
Data Index: 5666720 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0054. Min Act: -0.1700
Data Index: 5828741 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6616. Min Range: -5.6616
Max Act: 5.0054. Min Act: -0.1700
Data Index: 4916891 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19