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

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

Neuron 2950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5336. Min Act: -0.0001

Data Index: 400477 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6629. Min Act: -0.0001

Data Index: 603205 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5443. Min Act: -0.0001

Data Index: 525242 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6988. Min Act: -0.0001

Data Index: 741391 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5327. Min Act: -0.0001

Data Index: 296419 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.3937. Min Act: -0.0001

Data Index: 411269 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6551. Min Act: -0.0001

Data Index: 155522 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5417. Min Act: -0.0001

Data Index: 1034994 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.9187. Min Act: -0.0001

Data Index: 1164996 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.6983. Min Act: -0.0001

Data Index: 1249995 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.3482. Min Act: -0.0001

Data Index: 1116734 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.5595. Min Act: -0.0001

Data Index: 254658 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.4898. Min Act: -0.0001

Data Index: 592520 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.3604. Min Act: -0.0001

Data Index: 893591 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.3154. Min Act: -0.0001

Data Index: 256346 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.2779. Min Act: -0.0001

Data Index: 897186 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.2364. Min Act: -0.0001

Data Index: 756489 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.2004. Min Act: -0.0001

Data Index: 356147 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.3109. Min Act: -0.0001

Data Index: 316239 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 3.6988. Min Range: -3.6988

Max Act: 2.4373. Min Act: -0.0001

Data Index: 44599 (C4 (Web Text))

Max Activating Token Index: 790