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

Dataset: The Pile

Neuron 3995 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: 1.9666. Min Range: -1.9666

Max Act: 1.9666. Min Act: 0.0000

Data Index: 1339141 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.9308. Min Act: -0.0000

Data Index: 457130 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.8210. Min Act: -0.0000

Data Index: 739598 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.6453. Min Act: -0.0000

Data Index: 1765464 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.6253. Min Act: 0.0000

Data Index: 879968 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.6263. Min Act: -0.0000

Data Index: 585037 (The Pile)

Max Activating Token Index: 277

Text #6

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.5933. Min Act: -0.0000

Data Index: 1999129 (The Pile)

Max Activating Token Index: 76

Text #7

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1301677 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.7556. Min Act: -0.0000

Data Index: 862924 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.6467. Min Act: -0.0000

Data Index: 1990836 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.4894. Min Act: -0.0000

Data Index: 153705 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.4899. Min Act: -0.0000

Data Index: 1604916 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.4672. Min Act: -0.0000

Data Index: 452262 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1798617 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1307544 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.4854. Min Act: -0.0000

Data Index: 188495 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.5668. Min Act: -0.0000

Data Index: 704742 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.4339. Min Act: -0.0000

Data Index: 49300 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1022419 (The Pile)

Max Activating Token Index: 174

Text #19

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1918072 (The Pile)

Max Activating Token Index: 362