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

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

Neuron 142 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: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1306749 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1120054 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0585. Min Act: -0.0002

Data Index: 672839 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1286488 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0519. Min Act: -0.0001

Data Index: 928334 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0487. Min Act: -0.0002

Data Index: 904633 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1580456 (Python Code)

Max Activating Token Index: 193

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1071134 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1576192 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1149660 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0489. Min Act: -0.0002

Data Index: 678896 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1555797 (Python Code)

Max Activating Token Index: 506

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1646514 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1132595 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0510. Min Act: -0.0001

Data Index: 290592 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0491. Min Act: -0.0002

Data Index: 170628 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1540244 (Python Code)

Max Activating Token Index: 805

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1576472 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0509. Min Act: -0.0002

Data Index: 454400 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1578869 (Python Code)

Max Activating Token Index: 835