Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3260 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.6348. Min Act: -0.0000

Data Index: 4427 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.6081. Min Act: -0.0000

Data Index: 861844 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.5953. Min Act: -0.0000

Data Index: 685373 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.5213. Min Act: -0.0000

Data Index: 957698 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1149860 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.5298. Min Act: -0.0000

Data Index: 287505 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1204194 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1241913 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.5002. Min Act: -0.0000

Data Index: 220391 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1058729 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1120206 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4571. Min Act: -0.0000

Data Index: 882112 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.5063. Min Act: -0.0000

Data Index: 526670 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4722. Min Act: -0.0000

Data Index: 493421 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1087674 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1136632 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4650. Min Act: -0.0000

Data Index: 586156 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4812. Min Act: -0.0000

Data Index: 499857 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1216851 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.6348. Min Range: -0.6348

Max Act: 0.4312. Min Act: -0.0000

Data Index: 585082 (C4 (Web Text))

Max Activating Token Index: 686