Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 507 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1084510 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0001

Data Index: 972855 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0323. Min Act: -0.0001

Data Index: 616636 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0326. Min Act: -0.0001

Data Index: 451175 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0331. Min Act: -0.0001

Data Index: 263512 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1017838 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0322. Min Act: -0.0001

Data Index: 538667 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1149531 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1064884 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0312. Min Act: -0.0001

Data Index: 440249 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0313. Min Act: -0.0001

Data Index: 815164 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0295. Min Act: -0.0001

Data Index: 259504 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0295. Min Act: -0.0001

Data Index: 126506 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0290. Min Act: -0.0001

Data Index: 442044 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0291. Min Act: -0.0001

Data Index: 386586 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0303. Min Act: -0.0001

Data Index: 600934 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0302. Min Act: -0.0001

Data Index: 36808 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0312. Min Act: -0.0001

Data Index: 663649 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1106126 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0287. Min Act: -0.0001

Data Index: 882193 (C4 (Web Text))

Max Activating Token Index: 431