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

Dataset: The Pile

Neuron 3056 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1249263 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.8288. Min Act: -0.0000

Data Index: 652369 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.7313. Min Act: -0.0000

Data Index: 490424 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1148222 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.7408. Min Act: -0.0000

Data Index: 684322 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.7841. Min Act: -0.0000

Data Index: 760351 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1762743 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6806. Min Act: -0.0000

Data Index: 738879 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1479723 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6678. Min Act: -0.0000

Data Index: 780557 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1328282 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1985147 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5923. Min Act: -0.0000

Data Index: 924249 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5692. Min Act: -0.0000

Data Index: 387670 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1804354 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5845. Min Act: -0.0000

Data Index: 170881 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1774637 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1160085 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5965. Min Act: -0.0000

Data Index: 832419 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.8289. Min Range: -0.8289

Max Act: 0.5911. Min Act: -0.0000

Data Index: 672096 (The Pile)

Max Activating Token Index: 434