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

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

Neuron 2215 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0750. Min Range: -1.0750

Max Act: 1.0750. Min Act: -0.0000

Data Index: 678247 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.8105. Min Act: -0.0000

Data Index: 589998 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7529. Min Act: -0.0000

Data Index: 31114 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.7541. Min Act: -0.0000

Data Index: 740628 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5150. Min Act: -0.0000

Data Index: 584807 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5259. Min Act: -0.0000

Data Index: 156757 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4974. Min Act: -0.0000

Data Index: 653464 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1164088 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1074707 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1319518 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1321883 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1168643 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4774. Min Act: -0.0000

Data Index: 709884 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4587. Min Act: -0.0000

Data Index: 810063 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4673. Min Act: -0.0000

Data Index: 216571 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1136503 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4770. Min Act: -0.0000

Data Index: 607183 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4298. Min Act: -0.0000

Data Index: 924193 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4600. Min Act: -0.0000

Data Index: 640947 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.0750. Min Range: -1.0750

Max Act: 0.4253. Min Act: -0.0000

Data Index: 853862 (C4 (Web Text))

Max Activating Token Index: 533