Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2081 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.3702. Min Act: -0.1700
Data Index: 1637078 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.3074. Min Act: -0.1700
Data Index: 6314123 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.2760. Min Act: -0.1700
Data Index: 2048975 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.2760. Min Act: -0.1700
Data Index: 1205494 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.2603. Min Act: -0.1700
Data Index: 7019406 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.2603. Min Act: -0.1700
Data Index: 2544874 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.2446. Min Act: -0.1700
Data Index: 4942184 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1660. Min Act: -0.1700
Data Index: 4840209 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1502. Min Act: -0.1700
Data Index: 7557910 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1502. Min Act: -0.1700
Data Index: 8643587 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1502. Min Act: -0.1700
Data Index: 6152533 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1345. Min Act: -0.1700
Data Index: 7924282 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1345. Min Act: -0.1700
Data Index: 4938390 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1030. Min Act: -0.1700
Data Index: 5627973 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1187. Min Act: -0.1700
Data Index: 4911645 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1030. Min Act: -0.1700
Data Index: 2923003 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.1030. Min Act: -0.1700
Data Index: 4823898 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.0872. Min Act: -0.1700
Data Index: 233180 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.0714. Min Act: -0.1700
Data Index: 2299404 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3702. Min Range: -3.3702
Max Act: 3.0872. Min Act: -0.1700
Data Index: 7034530 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19