Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.7511. Min Act: -0.1700
Data Index: 5227266 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.5636. Min Act: -0.1700
Data Index: 2297049 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.5324. Min Act: -0.1700
Data Index: 3889001 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.5324. Min Act: -0.1700
Data Index: 7565712 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.5011. Min Act: -0.1700
Data Index: 4898443 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.5011. Min Act: -0.1700
Data Index: 5503345 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4699. Min Act: -0.1700
Data Index: 6138350 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4699. Min Act: -0.1700
Data Index: 126433 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4386. Min Act: -0.1700
Data Index: 4071741 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4386. Min Act: -0.1700
Data Index: 2817905 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4074. Min Act: -0.1700
Data Index: 3966215 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4074. Min Act: -0.1700
Data Index: 810580 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4074. Min Act: -0.1700
Data Index: 8457619 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4074. Min Act: -0.1700
Data Index: 5844200 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.4074. Min Act: -0.1700
Data Index: 7795230 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.3761. Min Act: -0.1700
Data Index: 8134813 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.3761. Min Act: -0.1700
Data Index: 5962480 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.3449. Min Act: -0.1700
Data Index: 3168851 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.3761. Min Act: -0.1700
Data Index: 6272837 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7511. Min Range: -4.7511
Max Act: 4.3449. Min Act: -0.1700
Data Index: 6070147 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19