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

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

Neuron 474 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.6130. Min Act: -0.0001

Data Index: 641493 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.6353. Min Act: -0.0001

Data Index: 61696 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1190019 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5904. Min Act: -0.0001

Data Index: 578273 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5929. Min Act: -0.0001

Data Index: 932407 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5407. Min Act: -0.0001

Data Index: 1301919 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5318. Min Act: -0.0001

Data Index: 630639 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5617. Min Act: -0.0001

Data Index: 1220874 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5406. Min Act: -0.0001

Data Index: 1174951 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5231. Min Act: -0.0001

Data Index: 354408 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5170. Min Act: -0.0001

Data Index: 1022825 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5644. Min Act: -0.0001

Data Index: 130806 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5249. Min Act: -0.0001

Data Index: 782956 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5742. Min Act: -0.0001

Data Index: 1346269 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5141. Min Act: -0.0001

Data Index: 160164 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5100. Min Act: -0.0001

Data Index: 439957 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5116. Min Act: -0.0001

Data Index: 408094 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.3788. Min Act: -0.0001

Data Index: 204308 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5017. Min Act: -0.0001

Data Index: 483127 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5007. Min Act: -0.0001

Data Index: 1301231 (C4 (Web Text))

Max Activating Token Index: 405