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

Dataset: The Pile

Neuron 2780 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: 0.8489. Min Range: -0.8489

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1409378 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.8060. Min Act: -0.0000

Data Index: 74622 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1882044 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.7775. Min Act: -0.0000

Data Index: 186676 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1238269 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.6092. Min Act: -0.0000

Data Index: 161188 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.6138. Min Act: -0.0000

Data Index: 8998 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5792. Min Act: -0.0000

Data Index: 777031 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1131553 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5731. Min Act: -0.0000

Data Index: 786451 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1998935 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1355417 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1776572 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1890613 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1142733 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1125482 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1392389 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5267. Min Act: -0.0000

Data Index: 318254 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5242. Min Act: -0.0000

Data Index: 738329 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1684004 (The Pile)

Max Activating Token Index: 710