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

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

Neuron 303 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: 1.7488. Min Range: -1.7488

Max Act: 1.6968. Min Act: -0.0000

Data Index: 745287 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.6821. Min Act: -0.0000

Data Index: 975562 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.4936. Min Act: -0.0000

Data Index: 1211456 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.6591. Min Act: -0.0000

Data Index: 702819 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.5753. Min Act: -0.0000

Data Index: 625521 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.7488. Min Act: -0.0000

Data Index: 1002328 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.6408. Min Act: -0.0000

Data Index: 2149 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.6378. Min Act: -0.0000

Data Index: 843420 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1039955 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.5335. Min Act: -0.0000

Data Index: 502213 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.5261. Min Act: -0.0000

Data Index: 132530 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.5368. Min Act: -0.0000

Data Index: 121722 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.5255. Min Act: -0.0000

Data Index: 732320 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.3889. Min Act: -0.0000

Data Index: 218058 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.4542. Min Act: -0.0000

Data Index: 224625 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.5514. Min Act: -0.0000

Data Index: 313741 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.4283. Min Act: -0.0000

Data Index: 1123530 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.4220. Min Act: -0.0000

Data Index: 490712 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.4259. Min Act: -0.0000

Data Index: 497111 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.7488. Min Range: -1.7488

Max Act: 1.4077. Min Act: -0.0000

Data Index: 127553 (C4 (Web Text))

Max Activating Token Index: 536