Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1496 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.8652. Min Act: -0.1700
Data Index: 2846291 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.8027. Min Act: -0.1700
Data Index: 4177966 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.7715. Min Act: -0.1700
Data Index: 5474647 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.6777. Min Act: -0.1700
Data Index: 7831256 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.5527. Min Act: -0.1700
Data Index: 4727117 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.5215. Min Act: -0.1700
Data Index: 666373 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.4902. Min Act: -0.1700
Data Index: 6414808 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.4902. Min Act: -0.1700
Data Index: 6516827 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.4902. Min Act: -0.1700
Data Index: 6533261 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.4590. Min Act: -0.1700
Data Index: 4940062 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3965. Min Act: -0.1700
Data Index: 570731 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3965. Min Act: -0.1700
Data Index: 2952238 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3652. Min Act: -0.1700
Data Index: 3189198 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3652. Min Act: -0.1700
Data Index: 8830915 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3340. Min Act: -0.1700
Data Index: 4450321 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3340. Min Act: -0.1700
Data Index: 5308312 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3340. Min Act: -0.1700
Data Index: 2614096 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.3340. Min Act: -0.1700
Data Index: 1443177 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.2715. Min Act: -0.1700
Data Index: 2406530 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8652. Min Range: -6.8652
Max Act: 6.2715. Min Act: -0.1700
Data Index: 4003519 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19