Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 178 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1034041 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0560. Min Act: -0.0002

Data Index: 136395 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0494. Min Act: -0.0002

Data Index: 4333 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0501. Min Act: -0.0002

Data Index: 566836 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0490. Min Act: -0.0002

Data Index: 931758 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0491. Min Act: -0.0002

Data Index: 467400 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0514. Min Act: -0.0002

Data Index: 706887 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0496. Min Act: -0.0002

Data Index: 52529 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1092136 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0467. Min Act: -0.0002

Data Index: 900113 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0431. Min Act: -0.0002

Data Index: 345273 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0465. Min Act: -0.0002

Data Index: 237245 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0451. Min Act: -0.0002

Data Index: 708648 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1106060 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0451. Min Act: -0.0002

Data Index: 421713 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0426. Min Act: -0.0002

Data Index: 221691 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0439. Min Act: -0.0002

Data Index: 434098 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1070618 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1203135 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0426. Min Act: -0.0001

Data Index: 643263 (C4 (Web Text))

Max Activating Token Index: 187