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

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

Neuron 2748 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0585. Min Act: -0.0001

Data Index: 199318 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0581. Min Act: -0.0001

Data Index: 753174 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0586. Min Act: -0.0001

Data Index: 117984 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0001

Data Index: 280468 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0542. Min Act: -0.0001

Data Index: 406303 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0527. Min Act: -0.0001

Data Index: 331372 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1652020 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0509. Min Act: -0.0001

Data Index: 948067 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0566. Min Act: -0.0001

Data Index: 972001 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0519. Min Act: -0.0001

Data Index: 247602 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1428308 (Python Code)

Max Activating Token Index: 682

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0477. Min Act: -0.0001

Data Index: 793964 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1037647 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1248057 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0496. Min Act: -0.0001

Data Index: 355170 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0494. Min Act: -0.0001

Data Index: 310136 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0493. Min Act: -0.0001

Data Index: 350531 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1419479 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0503. Min Act: -0.0001

Data Index: 50917 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1635564 (Python Code)

Max Activating Token Index: 834