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

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

Neuron 2957 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: 0.5756. Min Range: -0.5756

Max Act: 0.5756. Min Act: -0.0001

Data Index: 936969 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4710. Min Act: -0.0001

Data Index: 756933 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4367. Min Act: -0.0001

Data Index: 93473 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3935. Min Act: -0.0001

Data Index: 1130118 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3725. Min Act: -0.0001

Data Index: 47289 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3744. Min Act: -0.0002

Data Index: 582039 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3890. Min Act: -0.0001

Data Index: 221683 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3956. Min Act: -0.0002

Data Index: 667673 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3743. Min Act: -0.0001

Data Index: 1102747 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3714. Min Act: -0.0001

Data Index: 222000 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3544. Min Act: -0.0001

Data Index: 247570 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3533. Min Act: -0.0001

Data Index: 162195 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3635. Min Act: -0.0001

Data Index: 274643 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3480. Min Act: -0.0002

Data Index: 1274629 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3566. Min Act: -0.0002

Data Index: 577497 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3564. Min Act: -0.0002

Data Index: 1339993 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3667. Min Act: -0.0001

Data Index: 408864 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3464. Min Act: -0.0002

Data Index: 1277524 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3492. Min Act: -0.0001

Data Index: 838822 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3321. Min Act: -0.0002

Data Index: 42847 (C4 (Web Text))

Max Activating Token Index: 856