Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.6488. Min Act: -0.1700
Data Index: 6808476 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.6176. Min Act: -0.1700
Data Index: 3599089 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.6176. Min Act: -0.1700
Data Index: 116411 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.6176. Min Act: -0.1700
Data Index: 4502653 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.5863. Min Act: -0.1700
Data Index: 4340264 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.5238. Min Act: -0.1700
Data Index: 2342531 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.4613. Min Act: -0.1700
Data Index: 4091033 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.4613. Min Act: -0.1700
Data Index: 3856178 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.4301. Min Act: -0.1700
Data Index: 4910709 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.4613. Min Act: -0.1700
Data Index: 6343188 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3988. Min Act: -0.1700
Data Index: 2848909 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3676. Min Act: -0.1700
Data Index: 6353692 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3363. Min Act: -0.1700
Data Index: 7213587 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3051. Min Act: -0.1700
Data Index: 8764277 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3363. Min Act: -0.1700
Data Index: 3204256 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3051. Min Act: -0.1700
Data Index: 6586048 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.2738. Min Act: -0.1700
Data Index: 4506433 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3051. Min Act: -0.1700
Data Index: 3858111 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.3051. Min Act: -0.1700
Data Index: 6904476 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6488. Min Range: -6.6488
Max Act: 6.2738. Min Act: -0.1700
Data Index: 358372 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19