Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4075 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3521. Min Act: -0.0000

Data Index: 282817 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1551301 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3571. Min Act: -0.0000

Data Index: 651511 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.2847. Min Act: 0.0000

Data Index: 53509 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1522739 (Python Code)

Max Activating Token Index: 359

Text #5

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.1855. Min Act: -0.0000

Data Index: 1540573 (Python Code)

Max Activating Token Index: 407

Text #6

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.1458. Min Act: -0.0000

Data Index: 728512 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3513. Min Act: -0.0000

Data Index: 734802 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1567819 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1130126 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.1451. Min Act: 0.0000

Data Index: 1212831 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.0386. Min Act: 0.0000

Data Index: 1222804 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.1503. Min Act: -0.0000

Data Index: 867410 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.0575. Min Act: -0.0000

Data Index: 395265 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1270794 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.0530. Min Act: -0.0000

Data Index: 291781 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 1.4370. Min Range: -1.4370

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1299531 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.0395. Min Act: 0.0000

Data Index: 1277771 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1373163 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 1.4370. Min Range: -1.4370

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1351793 (C4 (Web Text))

Max Activating Token Index: 74