Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.5738. Min Act: -0.1700
Data Index: 2828549 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.4488. Min Act: -0.1700
Data Index: 5223842 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.3238. Min Act: -0.1700
Data Index: 4201449 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.2613. Min Act: -0.1700
Data Index: 3902594 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.2301. Min Act: -0.1700
Data Index: 273888 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.2301. Min Act: -0.1700
Data Index: 256350 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.1988. Min Act: -0.1700
Data Index: 369885 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.1676. Min Act: -0.1700
Data Index: 5796586 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.1363. Min Act: -0.1700
Data Index: 3199372 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.1363. Min Act: -0.1700
Data Index: 7580635 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.1363. Min Act: -0.1700
Data Index: 8741722 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.0738. Min Act: -0.1700
Data Index: 6384018 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.0426. Min Act: -0.1700
Data Index: 644117 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.0113. Min Act: -0.1700
Data Index: 3563362 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.0113. Min Act: -0.1700
Data Index: 646146 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5738. Min Range: -6.5738
Max Act: 6.0113. Min Act: -0.1700
Data Index: 5973342 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5738. Min Range: -6.5738
Max Act: 5.9801. Min Act: -0.1700
Data Index: 945212 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5738. Min Range: -6.5738
Max Act: 5.9488. Min Act: -0.1700
Data Index: 6689375 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5738. Min Range: -6.5738
Max Act: 5.9801. Min Act: -0.1700
Data Index: 3669218 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5738. Min Range: -6.5738
Max Act: 5.9488. Min Act: -0.1700
Data Index: 7681024 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19