Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1141 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.8661. Min Act: -0.0000

Data Index: 621427 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1400160 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7149. Min Act: -0.0000

Data Index: 841031 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7593. Min Act: -0.0000

Data Index: 689052 (The Pile)

Max Activating Token Index: 48

Text #4

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1650835 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1235986 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6899. Min Act: -0.0000

Data Index: 858893 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6874. Min Act: -0.0000

Data Index: 352726 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1261656 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1468823 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6590. Min Act: -0.0000

Data Index: 247538 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6788. Min Act: -0.0000

Data Index: 173641 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1402310 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6327. Min Act: -0.0000

Data Index: 989803 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6913. Min Act: -0.0000

Data Index: 115906 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.5485. Min Act: -0.0000

Data Index: 643681 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1939372 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1670326 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6283. Min Act: -0.0000

Data Index: 701920 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1727209 (The Pile)

Max Activating Token Index: 248