Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 465 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.5275. Min Act: -0.0000

Data Index: 550322 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.5175. Min Act: -0.0000

Data Index: 794218 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.5010. Min Act: -0.0000

Data Index: 130547 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1428245 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1973671 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.4179. Min Act: -0.0000

Data Index: 509441 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.4165. Min Act: -0.0000

Data Index: 923577 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.4006. Min Act: -0.0000

Data Index: 18952 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3898. Min Act: -0.0000

Data Index: 22017 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1648216 (The Pile)

Max Activating Token Index: 544

Text #10

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1168225 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3693. Min Act: -0.0000

Data Index: 522290 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1868933 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1138487 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3433. Min Act: -0.0000

Data Index: 941853 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3444. Min Act: -0.0000

Data Index: 207054 (The Pile)

Max Activating Token Index: 384

Text #16

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3422. Min Act: -0.0000

Data Index: 667350 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3219. Min Act: -0.0000

Data Index: 891746 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1691248 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.5275. Min Range: -0.5275

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1095425 (The Pile)

Max Activating Token Index: 586