Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1913 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.7738. Min Act: -0.1700
Data Index: 700000 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.7738. Min Act: -0.1700
Data Index: 5189916 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.7425. Min Act: -0.1700
Data Index: 6787878 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.7113. Min Act: -0.1700
Data Index: 8332571 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6488. Min Act: -0.1700
Data Index: 7041402 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6175. Min Act: -0.1700
Data Index: 1966296 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6175. Min Act: -0.1700
Data Index: 8184979 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6488. Min Act: -0.1700
Data Index: 1784429 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6488. Min Act: -0.1700
Data Index: 5032520 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6488. Min Act: -0.1700
Data Index: 6290712 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6175. Min Act: -0.1700
Data Index: 6193710 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.6488. Min Act: -0.1700
Data Index: 7442099 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5863. Min Act: -0.1700
Data Index: 7167413 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5863. Min Act: -0.1700
Data Index: 2643045 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5550. Min Act: -0.1700
Data Index: 2263565 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5550. Min Act: -0.1700
Data Index: 1204556 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5238. Min Act: -0.1700
Data Index: 4591026 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5238. Min Act: -0.1700
Data Index: 424035 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5238. Min Act: -0.1700
Data Index: 2671234 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7738. Min Range: -6.7738
Max Act: 6.5238. Min Act: -0.1700
Data Index: 2933810 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19