Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.5376. Min Act: -0.1700
Data Index: 5480057 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.5063. Min Act: -0.1700
Data Index: 4269289 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.5063. Min Act: -0.1700
Data Index: 7212388 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.5063. Min Act: -0.1700
Data Index: 7531567 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.4438. Min Act: -0.1700
Data Index: 4044259 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.4438. Min Act: -0.1700
Data Index: 7448436 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.3501. Min Act: -0.1700
Data Index: 1285878 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.3501. Min Act: -0.1700
Data Index: 5056574 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.3501. Min Act: -0.1700
Data Index: 4607933 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.3188. Min Act: -0.1700
Data Index: 6442853 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.2251. Min Act: -0.1700
Data Index: 8710045 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.2251. Min Act: -0.1700
Data Index: 7549676 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1938. Min Act: -0.1700
Data Index: 5219400 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1313. Min Act: -0.1700
Data Index: 5007408 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1626. Min Act: -0.1700
Data Index: 2311179 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1626. Min Act: -0.1700
Data Index: 5108032 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1626. Min Act: -0.1700
Data Index: 4450504 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1626. Min Act: -0.1700
Data Index: 8604051 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1313. Min Act: -0.1700
Data Index: 2341009 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5376. Min Range: -6.5376
Max Act: 6.1626. Min Act: -0.1700
Data Index: 2014211 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19