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

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

Neuron 2585 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3961. Min Act: -0.0003

Data Index: 772127 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.4066. Min Act: -0.0003

Data Index: 254546 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3451. Min Act: -0.0003

Data Index: 13747 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3442. Min Act: -0.0003

Data Index: 240483 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3418. Min Act: -0.0003

Data Index: 925441 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3457. Min Act: -0.0002

Data Index: 190687 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3342. Min Act: -0.0003

Data Index: 686726 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3223. Min Act: -0.0003

Data Index: 687248 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3187. Min Act: -0.0003

Data Index: 1208747 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3182. Min Act: -0.0003

Data Index: 1016774 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3175. Min Act: -0.0003

Data Index: 518840 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2980. Min Act: -0.0003

Data Index: 744935 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.3037. Min Act: -0.0003

Data Index: 918264 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2981. Min Act: -0.0002

Data Index: 1157538 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2846. Min Act: -0.0002

Data Index: 330167 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2882. Min Act: -0.0003

Data Index: 162641 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2877. Min Act: -0.0003

Data Index: 928697 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2781. Min Act: -0.0003

Data Index: 1279136 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2965. Min Act: -0.0003

Data Index: 239311 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.4066. Min Range: -0.4066

Max Act: 0.2958. Min Act: -0.0003

Data Index: 703381 (C4 (Web Text))

Max Activating Token Index: 145