Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.4334. Min Act: -0.1700
Data Index: 3484117 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.2146. Min Act: -0.1700
Data Index: 2592947 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.0896. Min Act: -0.1700
Data Index: 1522589 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.0896. Min Act: -0.1700
Data Index: 2200967 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.0896. Min Act: -0.1700
Data Index: 2839878 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.0584. Min Act: -0.1700
Data Index: 251992 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.0584. Min Act: -0.1700
Data Index: 4207438 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4334. Min Range: -4.4334
Max Act: 4.0271. Min Act: -0.1700
Data Index: 753861 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9959. Min Act: -0.1700
Data Index: 6654404 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9959. Min Act: -0.1700
Data Index: 3961300 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9959. Min Act: -0.1700
Data Index: 4635538 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9959. Min Act: -0.1700
Data Index: 2423801 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9646. Min Act: -0.1700
Data Index: 85209 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9646. Min Act: -0.1700
Data Index: 6983614 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9333. Min Act: -0.1700
Data Index: 602450 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9333. Min Act: -0.1700
Data Index: 7115837 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9333. Min Act: -0.1700
Data Index: 4743881 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.9021. Min Act: -0.1700
Data Index: 1459447 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.8708. Min Act: -0.1700
Data Index: 2027888 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4334. Min Range: -4.4334
Max Act: 3.8708. Min Act: -0.1700
Data Index: 6752678 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19