Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 78 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0006

Data Index: 281936 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1174713 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1307594 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0394. Min Act: -0.0006

Data Index: 862458 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0367. Min Act: -0.0006

Data Index: 8388 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0367. Min Act: -0.0006

Data Index: 127887 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0375. Min Act: -0.0006

Data Index: 1345234 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1215007 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1033149 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0365. Min Act: -0.0006

Data Index: 1208572 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0362. Min Act: -0.0006

Data Index: 251544 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0369. Min Act: -0.0006

Data Index: 278362 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0377. Min Act: -0.0006

Data Index: 12519 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0361. Min Act: -0.0006

Data Index: 540212 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0359. Min Act: -0.0006

Data Index: 608089 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0364. Min Act: -0.0006

Data Index: 36441 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0354. Min Act: -0.0006

Data Index: 816024 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0352. Min Act: -0.0006

Data Index: 251592 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0357. Min Act: -0.0006

Data Index: 322590 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0343. Min Act: -0.0006

Data Index: 412904 (C4 (Web Text))

Max Activating Token Index: 940