Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.7106. Min Act: -0.1700
Data Index: 5508249 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.4919. Min Act: -0.1700
Data Index: 1695771 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.3356. Min Act: -0.1700
Data Index: 3442672 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.3044. Min Act: -0.1700
Data Index: 1628594 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.2106. Min Act: -0.1700
Data Index: 6310617 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.2106. Min Act: -0.1700
Data Index: 2532026 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.2106. Min Act: -0.1700
Data Index: 2593088 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.1794. Min Act: -0.1700
Data Index: 1293056 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.1481. Min Act: -0.1700
Data Index: 5753107 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.1481. Min Act: -0.1700
Data Index: 6951437 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.1481. Min Act: -0.1700
Data Index: 6485569 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0856. Min Act: -0.1700
Data Index: 1189744 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0856. Min Act: -0.1700
Data Index: 144432 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0856. Min Act: -0.1700
Data Index: 6027293 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0544. Min Act: -0.1700
Data Index: 3987603 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.1169. Min Act: -0.1700
Data Index: 5331030 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0856. Min Act: -0.1700
Data Index: 336610 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0544. Min Act: -0.1700
Data Index: 4152057 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0544. Min Act: -0.1700
Data Index: 2896677 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7106. Min Range: -5.7106
Max Act: 5.0544. Min Act: -0.1700
Data Index: 3751999 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19