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

Dataset: The Pile

Neuron 4198 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0380. Min Range: -1.0380

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1753548 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 1.0380. Min Range: -1.0380

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1995493 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1633338 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.9379. Min Act: 0.0000

Data Index: 1156850 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8236. Min Act: -0.0000

Data Index: 639669 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1198569 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1374098 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7325. Min Act: -0.0000

Data Index: 844524 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7604. Min Act: -0.0000

Data Index: 446372 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7318. Min Act: 0.0000

Data Index: 1547531 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.8066. Min Act: -0.0000

Data Index: 379796 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7555. Min Act: -0.0000

Data Index: 168690 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1912448 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1808822 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1027086 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.6506. Min Act: -0.0000

Data Index: 988541 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.7332. Min Act: -0.0000

Data Index: 711809 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1906123 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.6370. Min Act: -0.0000

Data Index: 783119 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.0380. Min Range: -1.0380

Max Act: 0.6283. Min Act: -0.0000

Data Index: 45843 (The Pile)

Max Activating Token Index: 70