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

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

Neuron 5039 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.5385. Min Act: -0.0000

Data Index: 1270564 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.3551. Min Act: -0.0000

Data Index: 917519 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.2305. Min Act: -0.0000

Data Index: 330425 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.1280. Min Act: -0.0000

Data Index: 1012591 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.1214. Min Act: -0.0000

Data Index: 1017168 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.0768. Min Act: -0.0000

Data Index: 666845 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.0342. Min Act: -0.0000

Data Index: 1173081 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 2.5385. Min Range: -2.5385

Max Act: 2.1187. Min Act: -0.0000

Data Index: 796524 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.9866. Min Act: -0.0000

Data Index: 640453 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.8654. Min Act: -0.0000

Data Index: 318545 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.9640. Min Act: -0.0000

Data Index: 1353209 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.9621. Min Act: -0.0000

Data Index: 215383 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.8586. Min Act: -0.0000

Data Index: 683592 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.9403. Min Act: -0.0000

Data Index: 1589861 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.9315. Min Act: -0.0000

Data Index: 646092 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.9268. Min Act: -0.0000

Data Index: 818188 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.8728. Min Act: -0.0000

Data Index: 377175 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.8809. Min Act: -0.0000

Data Index: 345638 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.8564. Min Act: -0.0000

Data Index: 803666 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 2.5385. Min Range: -2.5385

Max Act: 1.9449. Min Act: -0.0000

Data Index: 191685 (C4 (Web Text))

Max Activating Token Index: 427