Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6541. Min Act: -0.0002

Data Index: 147496 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6370. Min Act: -0.0002

Data Index: 282664 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5913. Min Act: -0.0002

Data Index: 133114 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6522. Min Act: -0.0002

Data Index: 1300960 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5977. Min Act: -0.0002

Data Index: 1201857 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5949. Min Act: -0.0002

Data Index: 201429 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5847. Min Act: -0.0002

Data Index: 920543 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6246. Min Act: -0.0002

Data Index: 45081 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5899. Min Act: -0.0002

Data Index: 659918 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5679. Min Act: -0.0002

Data Index: 293768 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5630. Min Act: -0.0002

Data Index: 1259064 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5793. Min Act: -0.0002

Data Index: 374637 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5730. Min Act: -0.0002

Data Index: 477636 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5718. Min Act: -0.0002

Data Index: 589884 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5487. Min Act: -0.0002

Data Index: 686664 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5820. Min Act: -0.0002

Data Index: 1267305 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5380. Min Act: -0.0002

Data Index: 170767 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5407. Min Act: -0.0002

Data Index: 1323614 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5343. Min Act: -0.0002

Data Index: 451530 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5558. Min Act: -0.0002

Data Index: 420502 (C4 (Web Text))

Max Activating Token Index: 418