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

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

Neuron 667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0553. Min Act: -0.0001

Data Index: 813109 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1226848 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0527. Min Act: -0.0001

Data Index: 122666 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1330502 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0488. Min Act: -0.0001

Data Index: 796038 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1355363 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0448. Min Act: -0.0001

Data Index: 197276 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0466. Min Act: -0.0001

Data Index: 388430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1546676 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0414. Min Act: -0.0001

Data Index: 435191 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0315. Min Act: -0.0001

Data Index: 279941 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1059327 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0393. Min Act: -0.0001

Data Index: 368950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1198238 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1194214 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1101967 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0341. Min Act: -0.0001

Data Index: 457476 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1488465 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0367. Min Act: -0.0001

Data Index: 441172 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1336857 (C4 (Web Text))

Max Activating Token Index: 1023