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

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

Neuron 4278 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1241741 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.0444. Min Range: -1.0444

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1107126 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9322. Min Act: -0.0000

Data Index: 798126 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7963. Min Act: -0.0000

Data Index: 167417 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8375. Min Act: -0.0000

Data Index: 456661 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1142069 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7735. Min Act: -0.0000

Data Index: 836619 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7137. Min Act: -0.0000

Data Index: 463739 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6825. Min Act: -0.0000

Data Index: 505147 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7230. Min Act: -0.0000

Data Index: 770125 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1023031 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7206. Min Act: -0.0000

Data Index: 650632 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1116198 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7580. Min Act: -0.0000

Data Index: 470220 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7029. Min Act: -0.0000

Data Index: 990671 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6836. Min Act: 0.0000

Data Index: 712864 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7583. Min Act: -0.0000

Data Index: 367385 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6421. Min Act: -0.0000

Data Index: 665425 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7120. Min Act: -0.0000

Data Index: 513525 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6805. Min Act: -0.0000

Data Index: 704598 (C4 (Web Text))

Max Activating Token Index: 110