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

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

Neuron 5355 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1645. Min Range: -1.1645

Max Act: 1.1512. Min Act: -0.0001

Data Index: 564655 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.1645. Min Range: -1.1645

Max Act: 1.1645. Min Act: -0.0001

Data Index: 656705 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.1645. Min Range: -1.1645

Max Act: 1.0780. Min Act: -0.0001

Data Index: 1348806 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 1.1645. Min Range: -1.1645

Max Act: 1.1428. Min Act: -0.0001

Data Index: 785631 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.8187. Min Act: -0.0001

Data Index: 601925 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9592. Min Act: -0.0001

Data Index: 1247619 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9797. Min Act: -0.0001

Data Index: 1092595 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.1645. Min Range: -1.1645

Max Act: 1.0258. Min Act: -0.0001

Data Index: 753924 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.6299. Min Act: -0.0001

Data Index: 1218637 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9916. Min Act: -0.0001

Data Index: 46924 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.8060. Min Act: -0.0001

Data Index: 212689 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9506. Min Act: -0.0001

Data Index: 992786 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.7963. Min Act: -0.0001

Data Index: 592647 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9396. Min Act: -0.0001

Data Index: 248641 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9599. Min Act: -0.0001

Data Index: 836460 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9350. Min Act: -0.0001

Data Index: 75954 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9589. Min Act: -0.0001

Data Index: 676747 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1067071 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.8209. Min Act: -0.0002

Data Index: 1027598 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.1645. Min Range: -1.1645

Max Act: 0.8378. Min Act: -0.0001

Data Index: 1224659 (C4 (Web Text))

Max Activating Token Index: 335