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

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

Neuron 4727 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5962. Min Act: -0.0000

Data Index: 451996 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5650. Min Act: -0.0000

Data Index: 253992 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.5751. Min Act: -0.0000

Data Index: 538000 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4310. Min Act: -0.0001

Data Index: 1065167 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4914. Min Act: -0.0000

Data Index: 420813 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4499. Min Act: -0.0000

Data Index: 142327 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4512. Min Act: -0.0001

Data Index: 671045 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4178. Min Act: -0.0000

Data Index: 882523 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4343. Min Act: -0.0000

Data Index: 153272 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1302714 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1111093 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4091. Min Act: -0.0000

Data Index: 570747 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4089. Min Act: -0.0000

Data Index: 725547 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3578. Min Act: -0.0001

Data Index: 139539 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3833. Min Act: -0.0001

Data Index: 872135 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3686. Min Act: -0.0001

Data Index: 898337 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4058. Min Act: -0.0001

Data Index: 1309618 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1010449 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1295118 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.5962. Min Range: -0.5962

Max Act: 0.3862. Min Act: -0.0000

Data Index: 750580 (C4 (Web Text))

Max Activating Token Index: 871