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

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

Neuron 1909 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: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0001

Data Index: 945854 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0595. Min Act: -0.0001

Data Index: 661134 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0572. Min Act: -0.0001

Data Index: 174260 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0571. Min Act: -0.0001

Data Index: 541271 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0502. Min Act: -0.0001

Data Index: 861919 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1516197 (Python Code)

Max Activating Token Index: 878

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0500. Min Act: -0.0001

Data Index: 421360 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1101064 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0454. Min Act: -0.0002

Data Index: 513555 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0528. Min Act: -0.0002

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1418649 (Python Code)

Max Activating Token Index: 328

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0479. Min Act: -0.0001

Data Index: 701511 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1389188 (Python Code)

Max Activating Token Index: 724

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1113999 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1507529 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0480. Min Act: -0.0001

Data Index: 737263 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0515. Min Act: -0.0001

Data Index: 416775 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1083535 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0428. Min Act: -0.0001

Data Index: 374987 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1589234 (Python Code)

Max Activating Token Index: 308