Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.3086. Min Act: -0.1700
Data Index: 3220052 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.2774. Min Act: -0.1700
Data Index: 5201685 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.2149. Min Act: -0.1700
Data Index: 5163551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.1836. Min Act: -0.1700
Data Index: 4292156 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.1211. Min Act: -0.1700
Data Index: 4079760 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.1211. Min Act: -0.1700
Data Index: 8400647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.0898. Min Act: -0.1700
Data Index: 7507300 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.0898. Min Act: -0.1700
Data Index: 1866916 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.0586. Min Act: -0.1700
Data Index: 6948303 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.0273. Min Act: -0.1700
Data Index: 820086 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.0273. Min Act: -0.1700
Data Index: 6331045 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3086. Min Range: -4.3086
Max Act: 4.0586. Min Act: -0.1700
Data Index: 623149 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9961. Min Act: -0.1700
Data Index: 6148714 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9961. Min Act: -0.1700
Data Index: 6392718 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9335. Min Act: -0.1700
Data Index: 2049875 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9335. Min Act: -0.1700
Data Index: 3810502 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9023. Min Act: -0.1700
Data Index: 2416707 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9023. Min Act: -0.1700
Data Index: 4418419 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9023. Min Act: -0.1699
Data Index: 6346279 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3086. Min Range: -4.3086
Max Act: 3.9023. Min Act: -0.1700
Data Index: 4931425 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19