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

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

Neuron 3661 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: 1.7621. Min Range: -1.7621

Max Act: 1.7621. Min Act: -0.0000

Data Index: 240562 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.5401. Min Act: -0.0001

Data Index: 925876 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.2748. Min Act: -0.0000

Data Index: 481709 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.5001. Min Act: -0.0000

Data Index: 367621 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.5784. Min Act: -0.0000

Data Index: 802226 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.4721. Min Act: -0.0000

Data Index: 1272742 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.4785. Min Act: -0.0000

Data Index: 891511 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1114407 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.4684. Min Act: -0.0000

Data Index: 375231 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1344960 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.3646. Min Act: -0.0000

Data Index: 949626 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.3190. Min Act: -0.0001

Data Index: 353959 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.3992. Min Act: -0.0000

Data Index: 951586 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.2319. Min Act: -0.0001

Data Index: 522028 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.3000. Min Act: -0.0000

Data Index: 680840 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.3567. Min Act: -0.0001

Data Index: 980939 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.2963. Min Act: -0.0000

Data Index: 354034 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.2967. Min Act: -0.0001

Data Index: 217378 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.3183. Min Act: -0.0000

Data Index: 114323 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.7621. Min Range: -1.7621

Max Act: 1.2750. Min Act: -0.0000

Data Index: 680485 (C4 (Web Text))

Max Activating Token Index: 218