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

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

Neuron 4629 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.9300. Min Act: -0.0001

Data Index: 1220692 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.9094. Min Act: -0.0001

Data Index: 202901 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.3690. Min Act: -0.0000

Data Index: 424828 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.2702. Min Act: -0.0000

Data Index: 1283999 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.3437. Min Act: -0.0001

Data Index: 12702 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.9810. Min Act: -0.0000

Data Index: 902674 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.3792. Min Act: -0.0001

Data Index: 36505 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.0054. Min Act: -0.0001

Data Index: 1301440 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.9351. Min Act: -0.0000

Data Index: 470166 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.9778. Min Act: -0.0000

Data Index: 1159428 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.0721. Min Act: -0.0000

Data Index: 154717 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.0706. Min Act: -0.0001

Data Index: 1330354 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.6873. Min Act: -0.0000

Data Index: 1281154 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.0737. Min Act: -0.0001

Data Index: 783972 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 2.9300. Min Range: -2.9300

Max Act: 2.1895. Min Act: -0.0000

Data Index: 1039126 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.7506. Min Act: -0.0000

Data Index: 832026 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.8109. Min Act: -0.0001

Data Index: 623256 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.9029. Min Act: -0.0001

Data Index: 1258769 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.8486. Min Act: -0.0000

Data Index: 1167681 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 2.9300. Min Range: -2.9300

Max Act: 1.8108. Min Act: -0.0000

Data Index: 715082 (C4 (Web Text))

Max Activating Token Index: 238