Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2976 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.6024. Min Act: -0.0000

Data Index: 902684 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5682. Min Act: -0.0000

Data Index: 580331 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5344. Min Act: -0.0000

Data Index: 135366 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1213869 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5209. Min Act: -0.0000

Data Index: 419184 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5490. Min Act: -0.0000

Data Index: 48756 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4914. Min Act: -0.0001

Data Index: 724753 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5206. Min Act: -0.0001

Data Index: 907734 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4789. Min Act: -0.0000

Data Index: 211888 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5126. Min Act: -0.0000

Data Index: 872735 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5272. Min Act: -0.0000

Data Index: 704993 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4274. Min Act: -0.0000

Data Index: 836132 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4955. Min Act: -0.0000

Data Index: 520652 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4688. Min Act: -0.0000

Data Index: 511996 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4643. Min Act: -0.0000

Data Index: 612552 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4583. Min Act: -0.0000

Data Index: 465499 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4637. Min Act: -0.0001

Data Index: 510426 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4431. Min Act: -0.0000

Data Index: 94460 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4254. Min Act: -0.0000

Data Index: 174438 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4362. Min Act: -0.0000

Data Index: 849962 (C4 (Web Text))

Max Activating Token Index: 110