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

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

Neuron 876 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0002

Data Index: 390223 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0582. Min Act: -0.0002

Data Index: 93833 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0472. Min Act: -0.0002

Data Index: 247340 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0441. Min Act: -0.0002

Data Index: 67499 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0425. Min Act: -0.0002

Data Index: 556215 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0422. Min Act: -0.0002

Data Index: 820154 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0424. Min Act: -0.0002

Data Index: 847745 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1102053 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0403. Min Act: -0.0002

Data Index: 793901 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0403. Min Act: -0.0002

Data Index: 934367 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0386. Min Act: -0.0002

Data Index: 443893 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0394. Min Act: -0.0002

Data Index: 423730 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1257793 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0394. Min Act: -0.0002

Data Index: 345204 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0401. Min Act: -0.0002

Data Index: 935945 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1224407 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0386. Min Act: -0.0002

Data Index: 891823 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1273456 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0379. Min Act: -0.0002

Data Index: 543275 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0378. Min Act: -0.0002

Data Index: 713888 (C4 (Web Text))

Max Activating Token Index: 603