Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3621 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4353. Min Act: -0.0000

Data Index: 630415 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4373. Min Act: -0.0000

Data Index: 37634 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3800. Min Act: -0.0000

Data Index: 931912 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3505. Min Act: -0.0000

Data Index: 407929 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3562. Min Act: -0.0000

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3751. Min Act: -0.0000

Data Index: 336503 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1159464 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1176598 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1212439 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3288. Min Act: -0.0000

Data Index: 321269 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2824. Min Act: -0.0000

Data Index: 575521 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1182642 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1313304 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2431. Min Act: -0.0000

Data Index: 301348 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2518. Min Act: -0.0000

Data Index: 480543 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1325622 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2622. Min Act: -0.0000

Data Index: 820588 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2425. Min Act: -0.0000

Data Index: 864168 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2883. Min Act: -0.0000

Data Index: 858248 (C4 (Web Text))

Max Activating Token Index: 959