Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1812 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1567. Min Act: -0.0001

Data Index: 998340 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1466. Min Act: -0.0001

Data Index: 570173 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1466. Min Act: -0.0001

Data Index: 196166 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1285164 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1030324 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1340121 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1473. Min Act: -0.0001

Data Index: 176108 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1458. Min Act: -0.0001

Data Index: 90812 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1393. Min Act: -0.0001

Data Index: 351636 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1331. Min Act: -0.0001

Data Index: 199612 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1382. Min Act: -0.0001

Data Index: 895848 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1375. Min Act: -0.0001

Data Index: 701294 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1393. Min Act: -0.0001

Data Index: 56966 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1352557 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1301. Min Act: -0.0001

Data Index: 423473 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1299. Min Act: -0.0001

Data Index: 782461 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1334. Min Act: -0.0001

Data Index: 958919 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1250. Min Act: -0.0001

Data Index: 769243 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1253244 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1349305 (C4 (Web Text))

Max Activating Token Index: 470