Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3873 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.7266. Min Act: -0.0001

Data Index: 592952 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.8704. Min Act: -0.0001

Data Index: 768982 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.3153. Min Act: -0.0001

Data Index: 663917 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.2383. Min Act: -0.0001

Data Index: 1303123 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.3464. Min Act: -0.0001

Data Index: 146172 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.7424. Min Act: -0.0001

Data Index: 335823 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.1205. Min Act: -0.0001

Data Index: 63635 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.0709. Min Act: -0.0001

Data Index: 493795 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 5.8704. Min Range: -5.8704

Max Act: 5.0340. Min Act: -0.0001

Data Index: 2546 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.9147. Min Act: -0.0001

Data Index: 580945 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.9070. Min Act: -0.0001

Data Index: 1201387 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.8515. Min Act: -0.0001

Data Index: 267654 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.8165. Min Act: -0.0001

Data Index: 316338 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.8919. Min Act: -0.0001

Data Index: 1253388 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.6926. Min Act: -0.0001

Data Index: 854912 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.6463. Min Act: -0.0001

Data Index: 1119274 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.4596. Min Act: -0.0001

Data Index: 465394 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.8077. Min Act: -0.0001

Data Index: 115402 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.5946. Min Act: -0.0000

Data Index: 215634 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 5.8704. Min Range: -5.8704

Max Act: 4.6001. Min Act: -0.0001

Data Index: 1135994 (C4 (Web Text))

Max Activating Token Index: 585