Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.4492. Min Act: -0.1700
Data Index: 3001220 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.4179. Min Act: -0.1700
Data Index: 8827322 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3867. Min Act: -0.1700
Data Index: 6749173 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3554. Min Act: -0.1700
Data Index: 4550081 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3242. Min Act: -0.1700
Data Index: 1241463 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 5617693 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.3242. Min Act: -0.1700
Data Index: 542269 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1699
Data Index: 2344242 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 8483383 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 7572576 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2617. Min Act: -0.1700
Data Index: 8772886 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2617. Min Act: -0.1700
Data Index: 769273 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2617. Min Act: -0.1700
Data Index: 5804546 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2617. Min Act: -0.1700
Data Index: 7122357 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2617. Min Act: -0.1700
Data Index: 3302761 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2929. Min Act: -0.1700
Data Index: 7911246 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.1991. Min Act: -0.1700
Data Index: 3962872 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2304. Min Act: -0.1700
Data Index: 4234966 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.2617. Min Act: -0.1700
Data Index: 8463982 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4492. Min Range: -4.4492
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1141901 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19