Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.1238. Min Act: -0.1700
Data Index: 4728312 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0925. Min Act: -0.1700
Data Index: 75557 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0925. Min Act: -0.1700
Data Index: 6305271 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0925. Min Act: -0.1700
Data Index: 2582028 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0925. Min Act: -0.1700
Data Index: 6831050 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0613. Min Act: -0.1700
Data Index: 8654535 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0613. Min Act: -0.1700
Data Index: 4756893 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0300. Min Act: -0.1700
Data Index: 3200346 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0300. Min Act: -0.1700
Data Index: 3037073 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1238. Min Range: -4.1238
Max Act: 4.0300. Min Act: -0.1700
Data Index: 3026296 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9987. Min Act: -0.1700
Data Index: 8343369 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9987. Min Act: -0.1700
Data Index: 8458768 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9987. Min Act: -0.1700
Data Index: 930739 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9987. Min Act: -0.1700
Data Index: 1875713 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9987. Min Act: -0.1700
Data Index: 7723527 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9675. Min Act: -0.1700
Data Index: 8521988 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9675. Min Act: -0.1700
Data Index: 5884521 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9362. Min Act: -0.1700
Data Index: 7299652 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9675. Min Act: -0.1700
Data Index: 4824776 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1238. Min Range: -4.1238
Max Act: 3.9675. Min Act: -0.1700
Data Index: 5373114 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19