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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1327 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1413. Min Range: -2.1413

Max Act: 2.1413. Min Act: -0.0000

Data Index: 932869 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.7712. Min Act: -0.0000

Data Index: 223272 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.7632. Min Act: -0.0000

Data Index: 1005417 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.6960. Min Act: -0.0000

Data Index: 957223 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.6968. Min Act: -0.0000

Data Index: 64750 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1338099 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5668. Min Act: -0.0000

Data Index: 336473 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5545. Min Act: -0.0000

Data Index: 379498 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.6301. Min Act: -0.0000

Data Index: 382509 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5379. Min Act: -0.0000

Data Index: 578069 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.6072. Min Act: -0.0000

Data Index: 598234 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5100. Min Act: -0.0000

Data Index: 715119 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5672. Min Act: -0.0000

Data Index: 394714 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5576. Min Act: -0.0000

Data Index: 153516 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5200. Min Act: -0.0000

Data Index: 380609 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5126. Min Act: -0.0000

Data Index: 405970 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.5058. Min Act: -0.0000

Data Index: 1051745 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.4770. Min Act: -0.0000

Data Index: 517140 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.4746. Min Act: -0.0000

Data Index: 362222 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 2.1413. Min Range: -2.1413

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1092635 (C4 (Web Text))

Max Activating Token Index: 437