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

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

Neuron 3793 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0536. Min Range: -1.0536

Max Act: 1.0536. Min Act: -0.0001

Data Index: 791803 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9494. Min Act: -0.0001

Data Index: 714030 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9335. Min Act: -0.0001

Data Index: 1091265 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8883. Min Act: -0.0001

Data Index: 1182372 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8723. Min Act: -0.0001

Data Index: 4477 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8961. Min Act: -0.0001

Data Index: 791299 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8683. Min Act: -0.0001

Data Index: 568624 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8704. Min Act: -0.0001

Data Index: 397902 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8427. Min Act: -0.0001

Data Index: 765516 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9397. Min Act: -0.0001

Data Index: 1400507 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8772. Min Act: -0.0001

Data Index: 1136519 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8274. Min Act: -0.0001

Data Index: 1005466 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1016537 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8490. Min Act: -0.0001

Data Index: 461821 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8461. Min Act: -0.0001

Data Index: 178341 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8729. Min Act: -0.0001

Data Index: 716370 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8476. Min Act: -0.0001

Data Index: 652385 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8162. Min Act: -0.0001

Data Index: 1319686 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8310. Min Act: -0.0001

Data Index: 953985 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8794. Min Act: -0.0001

Data Index: 708575 (C4 (Web Text))

Max Activating Token Index: 1006