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

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

Neuron 750 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: 0.3304. Min Range: -0.3304

Max Act: 0.3304. Min Act: -0.0001

Data Index: 1580691 (Python Code)

Max Activating Token Index: 378

Text #1

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.3178. Min Act: -0.0000

Data Index: 551618 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.3149. Min Act: -0.0001

Data Index: 542690 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1208521 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.3069. Min Act: -0.0001

Data Index: 1624906 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1113396 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2993. Min Act: -0.0001

Data Index: 1344200 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2879. Min Act: -0.0001

Data Index: 1371487 (Python Code)

Max Activating Token Index: 360

Text #8

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2790. Min Act: -0.0000

Data Index: 6219 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2696. Min Act: -0.0000

Data Index: 259992 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1265339 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2712. Min Act: -0.0000

Data Index: 16036 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2533. Min Act: -0.0001

Data Index: 98962 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2722. Min Act: -0.0000

Data Index: 964117 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2664. Min Act: -0.0000

Data Index: 737320 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2712. Min Act: -0.0001

Data Index: 1517275 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2578. Min Act: -0.0001

Data Index: 704234 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2479. Min Act: -0.0000

Data Index: 29739 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2554. Min Act: -0.0000

Data Index: 382702 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.3304. Min Range: -0.3304

Max Act: 0.2555. Min Act: -0.0000

Data Index: 64653 (C4 (Web Text))

Max Activating Token Index: 254