Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1874 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2271. Min Range: -7.2271
Max Act: 7.2271. Min Act: -0.1700
Data Index: 2378329 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.9459. Min Act: -0.1700
Data Index: 2378330 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.8834. Min Act: -0.1700
Data Index: 6556069 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.8834. Min Act: -0.1700
Data Index: 3805910 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.8209. Min Act: -0.1700
Data Index: 2957728 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.7896. Min Act: -0.1700
Data Index: 1469304 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.7271. Min Act: -0.1700
Data Index: 7812113 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6959. Min Act: -0.1700
Data Index: 7668675 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6959. Min Act: -0.1700
Data Index: 2898696 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6646. Min Act: -0.1700
Data Index: 5787236 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6646. Min Act: -0.1700
Data Index: 8684358 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6334. Min Act: -0.1700
Data Index: 5869387 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6334. Min Act: -0.1700
Data Index: 3140806 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6021. Min Act: -0.1700
Data Index: 5158071 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.6021. Min Act: -0.1700
Data Index: 2113609 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.5709. Min Act: -0.1700
Data Index: 1261183 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.5084. Min Act: -0.1700
Data Index: 1852035 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.5084. Min Act: -0.1700
Data Index: 395837 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.5084. Min Act: -0.1700
Data Index: 347189 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2271. Min Range: -7.2271
Max Act: 6.4771. Min Act: -0.1700
Data Index: 4985690 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19