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

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

Neuron 3776 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.7480. Min Act: -0.0002

Data Index: 401093 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6260. Min Act: -0.0002

Data Index: 858994 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.6014. Min Act: -0.0002

Data Index: 1082118 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5441. Min Act: -0.0002

Data Index: 764245 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5621. Min Act: -0.0002

Data Index: 951089 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5596. Min Act: -0.0002

Data Index: 470654 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5271. Min Act: -0.0002

Data Index: 884224 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5370. Min Act: -0.0002

Data Index: 330231 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5124. Min Act: -0.0002

Data Index: 196419 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.5153. Min Act: -0.0002

Data Index: 794790 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4861. Min Act: -0.0002

Data Index: 1292713 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4669. Min Act: -0.0002

Data Index: 1111793 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4524. Min Act: -0.0002

Data Index: 1136400 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4403. Min Act: -0.0002

Data Index: 923575 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4321. Min Act: -0.0003

Data Index: 38839 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4463. Min Act: -0.0002

Data Index: 1012546 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4361. Min Act: -0.0002

Data Index: 54858 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4400. Min Act: -0.0002

Data Index: 1252715 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4186. Min Act: -0.0003

Data Index: 500511 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.4446. Min Act: -0.0002

Data Index: 1152588 (C4 (Web Text))

Max Activating Token Index: 1012