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

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

Neuron 81 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0529. Min Range: -1.0529

Max Act: 1.0529. Min Act: -0.0002

Data Index: 412830 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9666. Min Act: -0.0002

Data Index: 485984 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.8092. Min Act: -0.0002

Data Index: 648210 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9041. Min Act: -0.0001

Data Index: 932420 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9133. Min Act: -0.0002

Data Index: 1065930 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9311. Min Act: -0.0002

Data Index: 1100688 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9035. Min Act: -0.0002

Data Index: 638206 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9613. Min Act: -0.0001

Data Index: 607081 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9079. Min Act: -0.0001

Data Index: 273628 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9585. Min Act: -0.0001

Data Index: 929367 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9159. Min Act: -0.0002

Data Index: 734346 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9137. Min Act: -0.0002

Data Index: 1056971 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9434. Min Act: -0.0002

Data Index: 790448 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9578. Min Act: -0.0002

Data Index: 744176 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9204. Min Act: -0.0001

Data Index: 641999 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9079. Min Act: -0.0002

Data Index: 326286 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.8868. Min Act: -0.0001

Data Index: 113247 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.8864. Min Act: -0.0002

Data Index: 293281 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.9428. Min Act: -0.0001

Data Index: 1004653 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.0529. Min Range: -1.0529

Max Act: 0.8486. Min Act: -0.0002

Data Index: 557621 (C4 (Web Text))

Max Activating Token Index: 318