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

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

Neuron 421 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: 0.4373. Min Range: -0.4373

Max Act: 0.4373. Min Act: -0.0000

Data Index: 525737 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1092941 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3818. Min Act: 0.0000

Data Index: 1344363 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1277558 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3225. Min Act: -0.0000

Data Index: 848906 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3302. Min Act: -0.0000

Data Index: 12551 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3310. Min Act: -0.0000

Data Index: 591518 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1211759 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1102461 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2665. Min Act: -0.0000

Data Index: 942512 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2813. Min Act: -0.0000

Data Index: 96274 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2737. Min Act: -0.0000

Data Index: 315204 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2766. Min Act: -0.0000

Data Index: 546494 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2822. Min Act: -0.0000

Data Index: 744404 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2401. Min Act: -0.0000

Data Index: 117567 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2480. Min Act: -0.0000

Data Index: 823765 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1063776 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1179763 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2498. Min Act: -0.0000

Data Index: 278384 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2634. Min Act: -0.0000

Data Index: 725189 (C4 (Web Text))

Max Activating Token Index: 120