Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.4661. Min Act: -0.1700
Data Index: 8085849 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.2308. Min Act: -0.1700
Data Index: 2092948 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.1993. Min Act: -0.1700
Data Index: 3615205 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.1836. Min Act: -0.1700
Data Index: 6143817 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.1836. Min Act: -0.1700
Data Index: 4256425 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.1679. Min Act: -0.1700
Data Index: 6753238 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.1521. Min Act: -0.1700
Data Index: 7877161 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.1364. Min Act: -0.1700
Data Index: 4549710 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.1364. Min Act: -0.1700
Data Index: 3157102 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 6440945 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0891. Min Act: -0.1700
Data Index: 4709116 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 2658625 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0891. Min Act: -0.1700
Data Index: 7130443 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 6739138 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 4196697 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 2193693 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 2034190 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 7923546 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 4075022 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4661. Min Range: -3.4661
Max Act: 3.0734. Min Act: -0.1700
Data Index: 6630904 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19