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

Dataset: The Pile

Neuron 699 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.7489. Min Act: -0.0000

Data Index: 137512 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6421. Min Act: -0.0000

Data Index: 233943 (The Pile)

Max Activating Token Index: 299

Text #2

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6044. Min Act: -0.0000

Data Index: 481943 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1168957 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5242. Min Act: -0.0000

Data Index: 396017 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5249. Min Act: -0.0000

Data Index: 388642 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5232. Min Act: -0.0000

Data Index: 251332 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5307. Min Act: -0.0000

Data Index: 458997 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5103. Min Act: -0.0000

Data Index: 72104 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1821798 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4918. Min Act: -0.0000

Data Index: 858716 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4846. Min Act: -0.0000

Data Index: 556220 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4693. Min Act: -0.0000

Data Index: 766326 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1759969 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5016. Min Act: -0.0000

Data Index: 234798 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4938. Min Act: -0.0000

Data Index: 152141 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4888. Min Act: -0.0000

Data Index: 836357 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4917. Min Act: -0.0000

Data Index: 629705 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4807. Min Act: -0.0000

Data Index: 912550 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1790328 (The Pile)

Max Activating Token Index: 595