Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5947. Min Range: -6.5947
Max Act: 6.5947. Min Act: -0.1700
Data Index: 5832108 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5947. Min Range: -6.5947
Max Act: 6.5947. Min Act: -0.1700
Data Index: 1382088 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5947. Min Range: -6.5947
Max Act: 6.3135. Min Act: -0.1700
Data Index: 8681978 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.9385. Min Act: -0.1700
Data Index: 8059490 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.9385. Min Act: -0.1700
Data Index: 1778897 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.9072. Min Act: -0.1700
Data Index: 4234856 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.8760. Min Act: -0.1700
Data Index: 4343114 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.9072. Min Act: -0.1700
Data Index: 8623538 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.8447. Min Act: -0.1700
Data Index: 6597254 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.8447. Min Act: -0.1700
Data Index: 4402802 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.8135. Min Act: -0.1700
Data Index: 1028236 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.8760. Min Act: -0.1700
Data Index: 3306834 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.7822. Min Act: -0.1700
Data Index: 6045761 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.8135. Min Act: -0.1700
Data Index: 299648 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.7510. Min Act: -0.1700
Data Index: 16103 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.7510. Min Act: -0.1700
Data Index: 1778879 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.7510. Min Act: -0.1700
Data Index: 2284106 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.7510. Min Act: -0.1700
Data Index: 6969652 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.7197. Min Act: -0.1700
Data Index: 8045219 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5947. Min Range: -6.5947
Max Act: 5.6885. Min Act: -0.1700
Data Index: 6532624 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19