Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 151 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1685220 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1992528 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1889687 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1520419 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4123. Min Act: -0.0000

Data Index: 25174 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4112. Min Act: -0.0000

Data Index: 884800 (The Pile)

Max Activating Token Index: 909

Text #6

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3773. Min Act: -0.0000

Data Index: 83639 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1882852 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1002172 (The Pile)

Max Activating Token Index: 104

Text #9

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3742. Min Act: -0.0000

Data Index: 472942 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1679561 (The Pile)

Max Activating Token Index: 840

Text #11

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3173. Min Act: 0.0000

Data Index: 1708691 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1339855 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1860077 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3145. Min Act: -0.0000

Data Index: 759776 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3225. Min Act: -0.0000

Data Index: 260197 (The Pile)

Max Activating Token Index: 276

Text #16

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1957124 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1443690 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1644686 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3040. Min Act: -0.0000

Data Index: 923675 (The Pile)

Max Activating Token Index: 371