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

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

Neuron 1278 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: 0.6641. Min Range: -0.6641

Max Act: 0.6641. Min Act: -0.0001

Data Index: 231161 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6282. Min Act: -0.0000

Data Index: 734860 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1246520 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5709. Min Act: -0.0000

Data Index: 221267 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5534. Min Act: -0.0001

Data Index: 62952 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1270473 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5439. Min Act: -0.0000

Data Index: 763747 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1139001 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5444. Min Act: -0.0000

Data Index: 275294 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5188. Min Act: -0.0001

Data Index: 1288009 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5018. Min Act: -0.0000

Data Index: 256837 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5357. Min Act: -0.0000

Data Index: 367810 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1303882 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5501. Min Act: -0.0001

Data Index: 1466683 (Python Code)

Max Activating Token Index: 922

Text #14

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1116980 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4933. Min Act: -0.0000

Data Index: 326251 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1034094 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4566. Min Act: -0.0000

Data Index: 304383 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4698. Min Act: -0.0000

Data Index: 471917 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1255677 (C4 (Web Text))

Max Activating Token Index: 72