Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4105 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.3551. Min Act: -0.1700
Data Index: 2612497 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.2926. Min Act: -0.1700
Data Index: 4250453 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.2926. Min Act: -0.1700
Data Index: 3042753 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.2301. Min Act: -0.1700
Data Index: 5553650 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.2301. Min Act: -0.1700
Data Index: 5026103 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1988. Min Act: -0.1700
Data Index: 3839377 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1988. Min Act: -0.1700
Data Index: 7761535 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1676. Min Act: -0.1700
Data Index: 2258397 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1676. Min Act: -0.1680
Data Index: 5394909 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1676. Min Act: -0.1700
Data Index: 4915050 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1363. Min Act: -0.1700
Data Index: 306779 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1363. Min Act: -0.1700
Data Index: 2114207 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1676. Min Act: -0.1698
Data Index: 6304759 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1051. Min Act: -0.1699
Data Index: 7659735 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1363. Min Act: -0.1700
Data Index: 2414921 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1363. Min Act: -0.1700
Data Index: 3664739 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1051. Min Act: -0.1700
Data Index: 7253783 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1051. Min Act: -0.1700
Data Index: 2161069 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1051. Min Act: -0.1700
Data Index: 823056 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3551. Min Range: -5.3551
Max Act: 5.1051. Min Act: -0.1700
Data Index: 5197821 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19