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

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

Neuron 2826 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: 1.7760. Min Range: -1.7760

Max Act: 1.7760. Min Act: -0.0001

Data Index: 511388 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.7343. Min Act: -0.0001

Data Index: 474723 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.5763. Min Act: -0.0001

Data Index: 240911 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3816. Min Act: -0.0001

Data Index: 1338833 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.4280. Min Act: -0.0001

Data Index: 1158610 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1632158 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3999. Min Act: -0.0001

Data Index: 271946 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3437. Min Act: -0.0001

Data Index: 747900 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.2964. Min Act: -0.0000

Data Index: 530694 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3287. Min Act: -0.0001

Data Index: 35549 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3140. Min Act: -0.0001

Data Index: 402393 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3526. Min Act: -0.0000

Data Index: 578479 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3124. Min Act: -0.0000

Data Index: 1041353 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.2977. Min Act: -0.0000

Data Index: 1436693 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.2966. Min Act: -0.0000

Data Index: 514460 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.2864. Min Act: -0.0001

Data Index: 422331 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.2494. Min Act: -0.0001

Data Index: 511793 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.2680. Min Act: -0.0001

Data Index: 276539 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3242. Min Act: -0.0000

Data Index: 4959 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.7760. Min Range: -1.7760

Max Act: 1.3019. Min Act: -0.0001

Data Index: 978501 (C4 (Web Text))

Max Activating Token Index: 435