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

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

Neuron 25 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3690. Min Act: 0.0000

Data Index: 328409 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3427. Min Act: -0.0000

Data Index: 350685 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1104059 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3194. Min Act: -0.0000

Data Index: 97790 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3451. Min Act: -0.0000

Data Index: 371155 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3306. Min Act: -0.0000

Data Index: 285755 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3400. Min Act: 0.0000

Data Index: 3509 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3276. Min Act: 0.0000

Data Index: 545776 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3116. Min Act: -0.0000

Data Index: 208937 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2931. Min Act: -0.0000

Data Index: 989777 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.3129. Min Act: 0.0000

Data Index: 822639 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1263769 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2884. Min Act: 0.0000

Data Index: 619399 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2927. Min Act: -0.0000

Data Index: 475155 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2839. Min Act: 0.0000

Data Index: 1325042 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2902. Min Act: -0.0000

Data Index: 936838 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2830. Min Act: 0.0000

Data Index: 1036307 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2786. Min Act: -0.0000

Data Index: 322878 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1638550 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 0.3690. Min Range: -0.3690

Max Act: 0.2686. Min Act: 0.0000

Data Index: 467982 (C4 (Web Text))

Max Activating Token Index: 164