Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.7530. Min Act: -0.1700
Data Index: 8404578 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.7218. Min Act: -0.1700
Data Index: 6955035 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.6280. Min Act: -0.1700
Data Index: 2678122 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.6280. Min Act: -0.1700
Data Index: 316120 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5968. Min Act: -0.1700
Data Index: 4870733 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5968. Min Act: -0.1700
Data Index: 5703044 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5655. Min Act: -0.1700
Data Index: 6347320 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5655. Min Act: -0.1700
Data Index: 769769 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5343. Min Act: -0.1700
Data Index: 4631349 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5685926 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5343. Min Act: -0.1700
Data Index: 7728143 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5343. Min Act: -0.1700
Data Index: 8006969 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5343. Min Act: -0.1700
Data Index: 5151161 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5343. Min Act: -0.1700
Data Index: 2807384 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5465310 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5343. Min Act: -0.1700
Data Index: 3638861 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5742565 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5066974 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5030. Min Act: -0.1700
Data Index: 1871018 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7530. Min Range: -4.7530
Max Act: 4.5030. Min Act: -0.1700
Data Index: 6821210 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19