Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3041 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.4420. Min Act: -0.0001
Data Index: 298050 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.4337. Min Act: -0.0001
Data Index: 194828 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.3238. Min Act: -0.0001
Data Index: 1239558 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.3864. Min Act: -0.0001
Data Index: 1144538 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.3167. Min Act: -0.0001
Data Index: 1767993 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.2403. Min Act: -0.0001
Data Index: 407585 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.3152. Min Act: -0.0001
Data Index: 424826 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.2584. Min Act: -0.0001
Data Index: 852471 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.2359. Min Act: -0.0001
Data Index: 50978 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1751. Min Act: -0.0001
Data Index: 68741 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.2592. Min Act: -0.0001
Data Index: 1429408 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1067. Min Act: -0.0001
Data Index: 657896 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.2072. Min Act: -0.0001
Data Index: 1787067 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.2081. Min Act: -0.0001
Data Index: 541367 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1737. Min Act: -0.0001
Data Index: 149414 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1117. Min Act: -0.0001
Data Index: 719888 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1796. Min Act: -0.0001
Data Index: 1536702 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1614. Min Act: -0.0001
Data Index: 1702585 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1772. Min Act: -0.0001
Data Index: 1268086 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4420. Min Range: -1.4420
Max Act: 1.1828. Min Act: -0.0001
Data Index: 234460 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19