Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2003 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0006

Data Index: 643514 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0440. Min Act: -0.0006

Data Index: 578466 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0441. Min Act: -0.0006

Data Index: 690265 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0417. Min Act: -0.0006

Data Index: 662935 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0417. Min Act: -0.0006

Data Index: 1100096 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1178290 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0404. Min Act: -0.0006

Data Index: 225260 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0402. Min Act: -0.0006

Data Index: 99334 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0400. Min Act: -0.0006

Data Index: 986852 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0403. Min Act: -0.0006

Data Index: 636145 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0398. Min Act: -0.0005

Data Index: 1302002 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0389. Min Act: -0.0006

Data Index: 502073 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0407. Min Act: -0.0006

Data Index: 759911 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0387. Min Act: -0.0006

Data Index: 611940 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0395. Min Act: -0.0006

Data Index: 911987 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0387. Min Act: -0.0006

Data Index: 974078 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0391. Min Act: -0.0006

Data Index: 569373 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0400. Min Act: -0.0006

Data Index: 63649 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1050311 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0398. Min Act: -0.0006

Data Index: 895574 (C4 (Web Text))

Max Activating Token Index: 721