Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 434 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0522. Min Act: -0.0001

Data Index: 436851 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1025579 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0474. Min Act: -0.0001

Data Index: 343229 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0453. Min Act: -0.0001

Data Index: 872811 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1012327 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0418. Min Act: -0.0001

Data Index: 714331 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1207949 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1124282 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0422. Min Act: -0.0001

Data Index: 728381 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0375. Min Act: -0.0001

Data Index: 939858 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1105810 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0358. Min Act: -0.0001

Data Index: 549362 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0383. Min Act: -0.0001

Data Index: 403557 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0384. Min Act: -0.0001

Data Index: 837500 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0392. Min Act: -0.0001

Data Index: 514645 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1301683 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0359. Min Act: -0.0001

Data Index: 645367 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0373. Min Act: -0.0001

Data Index: 130092 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1104799 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0368. Min Act: -0.0001

Data Index: 251041 (C4 (Web Text))

Max Activating Token Index: 480