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

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

Neuron 4950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.0504. Min Act: -0.0001

Data Index: 1544437 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 3.2347. Min Range: -3.2347

Max Act: 3.2347. Min Act: -0.0001

Data Index: 1509231 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.8058. Min Act: -0.0001

Data Index: 1522682 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.7875. Min Act: -0.0001

Data Index: 1498585 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.8936. Min Act: -0.0000

Data Index: 1554629 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.7096. Min Act: -0.0000

Data Index: 1434808 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.6852. Min Act: -0.0001

Data Index: 1615306 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.6446. Min Act: -0.0000

Data Index: 1549419 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.4891. Min Act: -0.0001

Data Index: 1360158 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.4141. Min Act: -0.0000

Data Index: 1456505 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.4029. Min Act: -0.0001

Data Index: 1599410 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.3978. Min Act: -0.0001

Data Index: 1629641 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.6327. Min Act: -0.0001

Data Index: 1618576 (Python Code)

Max Activating Token Index: 444

Text #13

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.6508. Min Act: -0.0001

Data Index: 1561785 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.4774. Min Act: -0.0001

Data Index: 1508561 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.4899. Min Act: -0.0001

Data Index: 1648494 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.3370. Min Act: -0.0001

Data Index: 1637695 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.3459. Min Act: -0.0001

Data Index: 1409300 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.3306. Min Act: -0.0001

Data Index: 1541797 (Python Code)

Max Activating Token Index: 285

Text #19

Max Range: 3.2347. Min Range: -3.2347

Max Act: 2.4127. Min Act: -0.0000

Data Index: 1631567 (Python Code)

Max Activating Token Index: 695