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

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

Neuron 5552 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1347. Min Range: -3.1347

Max Act: 3.1347. Min Act: -0.0000

Data Index: 484704 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.8081. Min Act: -0.0000

Data Index: 262543 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.4933. Min Act: -0.0000

Data Index: 537094 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.5015. Min Act: 0.0000

Data Index: 1035979 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.3629. Min Act: -0.0000

Data Index: 181842 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.3196. Min Act: -0.0000

Data Index: 434216 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.3067. Min Act: 0.0000

Data Index: 208358 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.0334. Min Act: 0.0000

Data Index: 1326995 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.1268. Min Act: -0.0000

Data Index: 1207001 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.9602. Min Act: -0.0000

Data Index: 549796 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 3.1347. Min Range: -3.1347

Max Act: 2.0244. Min Act: -0.0000

Data Index: 6590 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.9727. Min Act: -0.0000

Data Index: 924888 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.9490. Min Act: 0.0000

Data Index: 599299 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.9373. Min Act: -0.0000

Data Index: 884240 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.9339. Min Act: 0.0001

Data Index: 290947 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.8940. Min Act: -0.0000

Data Index: 1107503 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.8766. Min Act: 0.0000

Data Index: 826774 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.8534. Min Act: -0.0000

Data Index: 627774 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.8366. Min Act: 0.0001

Data Index: 584390 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 3.1347. Min Range: -3.1347

Max Act: 1.8106. Min Act: -0.0000

Data Index: 666704 (C4 (Web Text))

Max Activating Token Index: 384