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

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

Neuron 4809 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.9588. Min Act: -0.0000

Data Index: 297100 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 2.0153. Min Range: -2.0153

Max Act: 2.0153. Min Act: -0.0000

Data Index: 231340 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.8203. Min Act: -0.0000

Data Index: 944031 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.7308. Min Act: -0.0000

Data Index: 658582 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.7596. Min Act: -0.0000

Data Index: 457711 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1152882 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.7494. Min Act: -0.0000

Data Index: 604337 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.5997. Min Act: -0.0000

Data Index: 130495 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.4830. Min Act: -0.0000

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.5117. Min Act: -0.0000

Data Index: 320449 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.4965. Min Act: -0.0000

Data Index: 797029 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.5230. Min Act: -0.0000

Data Index: 1265908 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.4533. Min Act: -0.0000

Data Index: 74267 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.3508. Min Act: -0.0000

Data Index: 145221 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1194884 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.3246. Min Act: -0.0000

Data Index: 393819 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.2578. Min Act: -0.0000

Data Index: 265230 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.2692. Min Act: -0.0000

Data Index: 733104 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1210956 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 2.0153. Min Range: -2.0153

Max Act: 1.1690. Min Act: -0.0000

Data Index: 315631 (C4 (Web Text))

Max Activating Token Index: 68