Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4744 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.9808. Min Act: -0.0000

Data Index: 940234 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8962. Min Act: 0.0000

Data Index: 122003 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8186. Min Act: -0.0000

Data Index: 915989 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1078482 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1301384 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8192. Min Act: 0.0001

Data Index: 1127989 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1155891 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7955. Min Act: -0.0000

Data Index: 800290 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7975. Min Act: 0.0000

Data Index: 703341 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1205351 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7712. Min Act: -0.0000

Data Index: 594614 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7711. Min Act: 0.0000

Data Index: 705649 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7527. Min Act: -0.0000

Data Index: 709335 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7386. Min Act: -0.0000

Data Index: 891036 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.6921. Min Act: -0.0000

Data Index: 82240 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1350464 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.6723. Min Act: -0.0000

Data Index: 96457 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1228124 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1304093 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.9808. Min Range: -0.9808

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1072614 (C4 (Web Text))

Max Activating Token Index: 927