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

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

Neuron 3542 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: 1.1124. Min Range: -1.1124

Max Act: 1.1124. Min Act: -0.0000

Data Index: 959829 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.1124. Min Range: -1.1124

Max Act: 1.0304. Min Act: -0.0000

Data Index: 743932 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1301213 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.1124. Min Range: -1.1124

Max Act: 1.0519. Min Act: -0.0000

Data Index: 887253 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.1124. Min Range: -1.1124

Max Act: 1.0450. Min Act: -0.0000

Data Index: 310216 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9869. Min Act: -0.0000

Data Index: 269401 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9872. Min Act: -0.0000

Data Index: 38188 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9842. Min Act: -0.0000

Data Index: 641299 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9586. Min Act: -0.0000

Data Index: 616609 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 1.1124. Min Range: -1.1124

Max Act: 1.0077. Min Act: -0.0000

Data Index: 671494 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9748. Min Act: -0.0000

Data Index: 940713 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9662. Min Act: -0.0000

Data Index: 120453 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9238. Min Act: -0.0000

Data Index: 882227 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1171263 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1282492 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9781. Min Act: -0.0000

Data Index: 832994 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9529. Min Act: -0.0000

Data Index: 921163 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9829. Min Act: -0.0000

Data Index: 363599 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9245. Min Act: -0.0000

Data Index: 83756 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.1124. Min Range: -1.1124

Max Act: 0.9172. Min Act: -0.0000

Data Index: 609162 (C4 (Web Text))

Max Activating Token Index: 298