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

Dataset: The Pile

Neuron 1917 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: 0.9362. Min Range: -0.9362

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1107765 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7677. Min Act: -0.0000

Data Index: 742645 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1926673 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1139838 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7668. Min Act: -0.0000

Data Index: 566013 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7299. Min Act: -0.0000

Data Index: 211857 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1709208 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1856100 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1016611 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1544131 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7522. Min Act: -0.0000

Data Index: 563584 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1867394 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.6343. Min Act: -0.0000

Data Index: 654596 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.6326. Min Act: -0.0000

Data Index: 749482 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.6034. Min Act: -0.0000

Data Index: 210118 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.6965. Min Act: -0.0000

Data Index: 795561 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.6481. Min Act: -0.0000

Data Index: 459771 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1751751 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.6108. Min Act: -0.0000

Data Index: 334207 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1605243 (The Pile)

Max Activating Token Index: 791