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

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

Neuron 686 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: 2.5864. Min Range: -2.5864

Max Act: 2.3633. Min Act: -0.0000

Data Index: 1569739 (Python Code)

Max Activating Token Index: 303

Text #1

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.5864. Min Act: -0.0000

Data Index: 890779 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.3423. Min Act: -0.0000

Data Index: 803558 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.3047. Min Act: -0.0000

Data Index: 1171040 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.1346. Min Act: -0.0000

Data Index: 236877 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.2467. Min Act: -0.0000

Data Index: 826796 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.1085. Min Act: -0.0000

Data Index: 517499 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.2070. Min Act: -0.0000

Data Index: 728687 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.3059. Min Act: -0.0000

Data Index: 1157815 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 2.5864. Min Range: -2.5864

Max Act: 1.9316. Min Act: -0.0000

Data Index: 576825 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.1578. Min Act: -0.0000

Data Index: 707190 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.2656. Min Act: -0.0000

Data Index: 977619 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.5135. Min Act: -0.0000

Data Index: 1580789 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 2.5864. Min Range: -2.5864

Max Act: 1.9419. Min Act: -0.0000

Data Index: 530403 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.0469. Min Act: -0.0000

Data Index: 775957 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 2.5864. Min Range: -2.5864

Max Act: 1.9101. Min Act: -0.0000

Data Index: 1288292 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.0149. Min Act: -0.0000

Data Index: 283006 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 2.5864. Min Range: -2.5864

Max Act: 1.9009. Min Act: -0.0000

Data Index: 879840 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.0145. Min Act: -0.0000

Data Index: 1316739 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 2.5864. Min Range: -2.5864

Max Act: 2.0014. Min Act: -0.0000

Data Index: 626968 (C4 (Web Text))

Max Activating Token Index: 638