Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1945 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5789. Min Act: -0.0001

Data Index: 650164 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5374. Min Act: -0.0001

Data Index: 184058 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5172. Min Act: -0.0001

Data Index: 837465 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5178. Min Act: -0.0001

Data Index: 677729 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5024. Min Act: -0.0001

Data Index: 287984 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1111929 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5463. Min Act: -0.0001

Data Index: 96742 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4822. Min Act: -0.0001

Data Index: 457432 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4613. Min Act: -0.0001

Data Index: 674958 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4640. Min Act: -0.0001

Data Index: 1298751 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1352008 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4727. Min Act: -0.0001

Data Index: 877407 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4551. Min Act: -0.0001

Data Index: 1304108 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4396. Min Act: -0.0001

Data Index: 241180 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4311. Min Act: -0.0001

Data Index: 860888 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4290. Min Act: -0.0001

Data Index: 453714 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4584. Min Act: -0.0001

Data Index: 963335 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4291. Min Act: -0.0001

Data Index: 1334150 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4052. Min Act: -0.0001

Data Index: 734835 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1287541 (C4 (Web Text))

Max Activating Token Index: 354