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

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

Neuron 3279 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5369. Min Act: -0.0000

Data Index: 290872 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5152. Min Act: -0.0001

Data Index: 676227 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5163. Min Act: -0.0001

Data Index: 1163280 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5344. Min Act: -0.0001

Data Index: 558731 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4822. Min Act: -0.0000

Data Index: 883300 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4878. Min Act: -0.0001

Data Index: 615703 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4688. Min Act: -0.0000

Data Index: 777458 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4737. Min Act: -0.0000

Data Index: 291474 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4870. Min Act: -0.0000

Data Index: 207496 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4657. Min Act: -0.0001

Data Index: 878834 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4396. Min Act: -0.0001

Data Index: 305059 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4385. Min Act: -0.0001

Data Index: 4029 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4507. Min Act: -0.0001

Data Index: 110285 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4393. Min Act: -0.0000

Data Index: 704980 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4345. Min Act: -0.0001

Data Index: 363001 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4194. Min Act: -0.0000

Data Index: 29895 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4324. Min Act: -0.0000

Data Index: 457155 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4115. Min Act: -0.0000

Data Index: 487832 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4115. Min Act: -0.0000

Data Index: 710805 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4360. Min Act: -0.0000

Data Index: 622125 (C4 (Web Text))

Max Activating Token Index: 452