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

Dataset: The Pile

Neuron 1693 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: 0.3370. Min Range: -0.3370

Max Act: 0.3370. Min Act: -0.0000

Data Index: 340613 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1043452 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1855725 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2437. Min Act: -0.0000

Data Index: 371264 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2583. Min Act: -0.0000

Data Index: 696991 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1185579 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2515. Min Act: -0.0000

Data Index: 909507 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2326. Min Act: -0.0000

Data Index: 798661 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2336. Min Act: -0.0000

Data Index: 833967 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1377603 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1144980 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2335. Min Act: -0.0000

Data Index: 874849 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2210. Min Act: -0.0000

Data Index: 761776 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1084448 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1699522 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1867235 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2084. Min Act: -0.0000

Data Index: 58771 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2213. Min Act: -0.0000

Data Index: 572279 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2144. Min Act: -0.0000

Data Index: 215918 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 0.3370. Min Range: -0.3370

Max Act: 0.2212. Min Act: -0.0000

Data Index: 627716 (The Pile)

Max Activating Token Index: 281