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

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

Neuron 1699 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: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0001

Data Index: 663170 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0470. Min Act: -0.0002

Data Index: 519145 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1298739 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0471. Min Act: -0.0002

Data Index: 736536 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0454. Min Act: -0.0002

Data Index: 33750 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0448. Min Act: -0.0001

Data Index: 771000 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0455. Min Act: -0.0001

Data Index: 216220 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0459. Min Act: -0.0002

Data Index: 500353 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0468. Min Act: -0.0002

Data Index: 355239 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0456. Min Act: -0.0002

Data Index: 790022 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0435. Min Act: -0.0001

Data Index: 69257 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0443. Min Act: -0.0002

Data Index: 54049 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0461. Min Act: -0.0002

Data Index: 355259 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0436. Min Act: -0.0002

Data Index: 951579 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0436. Min Act: -0.0002

Data Index: 171372 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1193610 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0434. Min Act: -0.0002

Data Index: 766811 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0439. Min Act: -0.0001

Data Index: 536781 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1318818 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0424. Min Act: -0.0002

Data Index: 874331 (C4 (Web Text))

Max Activating Token Index: 693