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

Dataset: The Pile

Neuron 552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.2214. Min Act: -0.0000

Data Index: 1721137 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.4735. Min Act: -0.0000

Data Index: 1033610 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1270. Min Act: -0.0000

Data Index: 1339795 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0885. Min Act: -0.0000

Data Index: 1939096 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0535. Min Act: -0.0000

Data Index: 924714 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.8352. Min Act: -0.0000

Data Index: 895071 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.9412. Min Act: -0.0000

Data Index: 1626182 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.7564. Min Act: -0.0000

Data Index: 1895143 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.6115. Min Act: -0.0000

Data Index: 181823 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.7525. Min Act: -0.0000

Data Index: 610058 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.3307. Min Act: -0.0000

Data Index: 1633181 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.3741. Min Act: -0.0000

Data Index: 1682147 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.3492. Min Act: -0.0000

Data Index: 1377282 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1726429 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.1972. Min Act: -0.0000

Data Index: 658443 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.3200. Min Act: -0.0000

Data Index: 1419876 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.3185. Min Act: -0.0000

Data Index: 673641 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.3095. Min Act: -0.0000

Data Index: 1006705 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.3075. Min Act: -0.0000

Data Index: 442419 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 3.4735. Min Range: -3.4735

Max Act: 2.2315. Min Act: -0.0000

Data Index: 1638162 (The Pile)

Max Activating Token Index: 910