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

Dataset: The Pile

Neuron 2107 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.4084. Min Act: -0.0000

Data Index: 186924 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1860995 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1036326 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1119645 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3645. Min Act: -0.0000

Data Index: 566626 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2984. Min Act: -0.0000

Data Index: 418430 (The Pile)

Max Activating Token Index: 909

Text #6

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1992535 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1384366 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1361740 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1659368 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3330. Min Act: -0.0000

Data Index: 742948 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1191646 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1676240 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1669186 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1637928 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3024. Min Act: -0.0000

Data Index: 593051 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2658. Min Act: -0.0000

Data Index: 562198 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1673360 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2984. Min Act: -0.0000

Data Index: 522590 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1104197 (The Pile)

Max Activating Token Index: 616