Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4857. Min Range: -12.4857
Max Act: 12.4857. Min Act: -0.1700
Data Index: 6298257 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.7982. Min Act: -0.1700
Data Index: 1484951 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.5482. Min Act: -0.1700
Data Index: 5657191 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.5482. Min Act: -0.1700
Data Index: 2637967 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.4857. Min Act: -0.1700
Data Index: 7304892 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.3607. Min Act: -0.1700
Data Index: 6361007 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.2357. Min Act: -0.1700
Data Index: 8257611 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.1732. Min Act: -0.1700
Data Index: 8531097 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4857. Min Range: -12.4857
Max Act: 11.1107. Min Act: -0.1700
Data Index: 8295868 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.9857. Min Act: -0.1700
Data Index: 2909035 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.9857. Min Act: -0.1700
Data Index: 1990869 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.9232. Min Act: -0.1700
Data Index: 5331512 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.8607. Min Act: -0.1700
Data Index: 4110121 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.8607. Min Act: -0.1700
Data Index: 5847313 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.7982. Min Act: -0.1700
Data Index: 3720613 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.7982. Min Act: -0.1700
Data Index: 5302393 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.7357. Min Act: -0.1700
Data Index: 2860490 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.7357. Min Act: -0.1700
Data Index: 5086499 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.7357. Min Act: -0.1700
Data Index: 6766940 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4857. Min Range: -12.4857
Max Act: 10.7357. Min Act: -0.1700
Data Index: 788575 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19