Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1316 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.8343. Min Act: -0.1700
Data Index: 6954802 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.8655. Min Act: -0.1700
Data Index: 2889987 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.7405. Min Act: -0.1700
Data Index: 4132782 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.6155. Min Act: -0.1700
Data Index: 8747278 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.6155. Min Act: -0.1700
Data Index: 7202936 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.5843. Min Act: -0.1700
Data Index: 7148633 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.5530. Min Act: -0.1700
Data Index: 7076718 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.5530. Min Act: -0.1700
Data Index: 172686 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.5218. Min Act: -0.1700
Data Index: 1112038 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.5218. Min Act: -0.1700
Data Index: 2417799 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.5530. Min Act: -0.1700
Data Index: 1047032 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.5218. Min Act: -0.1700
Data Index: 2699985 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.4593. Min Act: -0.1700
Data Index: 1116446 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.4280. Min Act: -0.1700
Data Index: 6716528 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.4280. Min Act: -0.1700
Data Index: 4623829 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.4280. Min Act: -0.1700
Data Index: 1966752 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.3968. Min Act: -0.1700
Data Index: 2833470 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.3655. Min Act: -0.1700
Data Index: 1047031 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.3655. Min Act: -0.1700
Data Index: 4310901 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8655. Min Range: -6.8655
Max Act: 6.3343. Min Act: -0.1700
Data Index: 2021624 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19