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

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

Neuron 2796 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: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0001

Data Index: 90346 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0646. Min Act: -0.0001

Data Index: 446896 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0640. Min Act: -0.0001

Data Index: 935194 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0594. Min Act: -0.0001

Data Index: 387766 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0606. Min Act: -0.0001

Data Index: 323913 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0560. Min Act: -0.0001

Data Index: 228078 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0574. Min Act: -0.0001

Data Index: 646037 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0531. Min Act: -0.0001

Data Index: 909659 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0544. Min Act: -0.0001

Data Index: 592418 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0530. Min Act: -0.0001

Data Index: 918309 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0531. Min Act: -0.0001

Data Index: 824208 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0482. Min Act: -0.0001

Data Index: 285266 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1202503 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0501. Min Act: -0.0001

Data Index: 906643 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0499. Min Act: -0.0001

Data Index: 788614 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1147341 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0483. Min Act: -0.0001

Data Index: 487377 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0502. Min Act: -0.0001

Data Index: 845443 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0495. Min Act: -0.0001

Data Index: 323297 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0485. Min Act: -0.0001

Data Index: 635393 (C4 (Web Text))

Max Activating Token Index: 24