Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.8263. Min Act: -0.1700
Data Index: 651388 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.8263. Min Act: -0.1700
Data Index: 3249778 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.6388. Min Act: -0.1700
Data Index: 3257871 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.5763. Min Act: -0.1700
Data Index: 8233689 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.3888. Min Act: -0.1700
Data Index: 4910965 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.3263. Min Act: -0.1700
Data Index: 5941094 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.3263. Min Act: -0.1700
Data Index: 2735280 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.3263. Min Act: -0.1700
Data Index: 7101682 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.2638. Min Act: -0.1700
Data Index: 994032 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.2013. Min Act: -0.1700
Data Index: 7537260 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.2013. Min Act: -0.1700
Data Index: 2532045 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.2013. Min Act: -0.1700
Data Index: 346108 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.2013. Min Act: -0.1700
Data Index: 1826322 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.2013. Min Act: -0.1700
Data Index: 4519939 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.2013. Min Act: -0.1700
Data Index: 1478892 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.1388. Min Act: -0.1700
Data Index: 735008 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.1388. Min Act: -0.1700
Data Index: 6948306 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.1388. Min Act: -0.1700
Data Index: 2996229 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.1388. Min Act: -0.1700
Data Index: 6737502 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8263. Min Range: -8.8263
Max Act: 8.1388. Min Act: -0.1700
Data Index: 7379953 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19