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

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

Neuron 1555 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.5123. Min Act: -0.0001

Data Index: 1206022 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.5415. Min Act: -0.0001

Data Index: 1032517 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.5195. Min Act: -0.0000

Data Index: 454823 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4826. Min Act: -0.0001

Data Index: 995590 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.5011. Min Act: -0.0000

Data Index: 239218 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4877. Min Act: -0.0001

Data Index: 779872 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4692. Min Act: -0.0001

Data Index: 1200058 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4625. Min Act: -0.0001

Data Index: 766191 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4543. Min Act: -0.0001

Data Index: 391395 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4700. Min Act: -0.0001

Data Index: 579485 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1184088 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4933. Min Act: -0.0001

Data Index: 1241437 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4750. Min Act: -0.0001

Data Index: 704885 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4726. Min Act: -0.0001

Data Index: 311950 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4498. Min Act: -0.0001

Data Index: 926473 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4494. Min Act: -0.0001

Data Index: 1331556 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4343. Min Act: -0.0001

Data Index: 538454 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4306. Min Act: -0.0001

Data Index: 201262 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4391. Min Act: -0.0001

Data Index: 329086 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.5415. Min Range: -0.5415

Max Act: 0.4442. Min Act: -0.0000

Data Index: 962661 (C4 (Web Text))

Max Activating Token Index: 381