Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.3734. Min Act: -0.1700
Data Index: 4237028 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.2797. Min Act: -0.1700
Data Index: 8061091 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.2172. Min Act: -0.1700
Data Index: 5159341 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.2172. Min Act: -0.1700
Data Index: 2357504 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.1859. Min Act: -0.1700
Data Index: 301698 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.1859. Min Act: -0.1700
Data Index: 2948965 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.1859. Min Act: -0.1700
Data Index: 2941265 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.1547. Min Act: -0.1700
Data Index: 6380897 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0922. Min Act: -0.1700
Data Index: 531046 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.1234. Min Act: -0.1700
Data Index: 4566619 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.1234. Min Act: -0.1700
Data Index: 7239929 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0922. Min Act: -0.1700
Data Index: 3615229 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0922. Min Act: -0.1700
Data Index: 6914749 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0609. Min Act: -0.1700
Data Index: 2478542 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0922. Min Act: -0.1700
Data Index: 4534660 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0297. Min Act: -0.1700
Data Index: 1534108 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0609. Min Act: -0.1700
Data Index: 918361 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0609. Min Act: -0.1700
Data Index: 1065734 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0297. Min Act: -0.1700
Data Index: 5743330 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3734. Min Range: -6.3734
Max Act: 6.0297. Min Act: -0.1700
Data Index: 596982 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19