Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 32 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0006

Data Index: 111783 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0424. Min Act: -0.0006

Data Index: 41799 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1299664 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0419. Min Act: -0.0006

Data Index: 284535 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0384. Min Act: -0.0006

Data Index: 847473 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0381. Min Act: -0.0007

Data Index: 1255119 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1011992 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0375. Min Act: -0.0006

Data Index: 276885 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0382. Min Act: -0.0006

Data Index: 745062 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0372. Min Act: -0.0006

Data Index: 160165 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0370. Min Act: -0.0006

Data Index: 367617 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0364. Min Act: -0.0006

Data Index: 406774 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0362. Min Act: -0.0006

Data Index: 759319 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0353. Min Act: -0.0006

Data Index: 1255754 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1008804 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0353. Min Act: -0.0006

Data Index: 943842 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1309550 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0347. Min Act: -0.0005

Data Index: 677463 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0348. Min Act: -0.0006

Data Index: 297222 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0340. Min Act: -0.0006

Data Index: 528328 (C4 (Web Text))

Max Activating Token Index: 246