Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4013 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.5729. Min Act: -0.1700
Data Index: 1611380 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.5104. Min Act: -0.1700
Data Index: 3166309 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.4166. Min Act: -0.1700
Data Index: 5367718 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.3229. Min Act: -0.1700
Data Index: 5731269 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1979. Min Act: -0.1700
Data Index: 1284325 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1979. Min Act: -0.1700
Data Index: 6845051 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1979. Min Act: -0.1700
Data Index: 8214702 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1979. Min Act: -0.1700
Data Index: 1847158 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1354. Min Act: -0.1700
Data Index: 5218534 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1354. Min Act: -0.1700
Data Index: 5291077 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1354. Min Act: -0.1700
Data Index: 5461315 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1041. Min Act: -0.1700
Data Index: 1551938 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.1041. Min Act: -0.1700
Data Index: 929938 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.0729. Min Act: -0.1700
Data Index: 1027861 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.0729. Min Act: -0.1700
Data Index: 2457 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.0729. Min Act: -0.1700
Data Index: 1908154 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.0416. Min Act: -0.1700
Data Index: 6684405 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.0416. Min Act: -0.1700
Data Index: 3328761 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.0416. Min Act: -0.1700
Data Index: 3553957 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5729. Min Range: -7.5729
Max Act: 7.0416. Min Act: -0.1700
Data Index: 1000197 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19