Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.4110. Min Act: -0.0001

Data Index: 488646 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.2787. Min Act: -0.0001

Data Index: 356604 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.1643. Min Act: -0.0001

Data Index: 1208852 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.1161. Min Act: -0.0001

Data Index: 557618 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.1279. Min Act: -0.0001

Data Index: 21761 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.0634. Min Act: -0.0001

Data Index: 564643 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.0694. Min Act: -0.0001

Data Index: 776271 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.1312. Min Act: -0.0001

Data Index: 643887 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.0091. Min Act: -0.0001

Data Index: 1251796 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.0204. Min Act: -0.0001

Data Index: 655994 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9466. Min Act: -0.0001

Data Index: 1253554 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1253012 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.0296. Min Act: -0.0001

Data Index: 319355 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9592. Min Act: -0.0001

Data Index: 49823 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9451. Min Act: -0.0001

Data Index: 517657 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9111. Min Act: -0.0001

Data Index: 522259 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9331. Min Act: -0.0001

Data Index: 335424 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9000. Min Act: -0.0001

Data Index: 669935 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9781. Min Act: -0.0001

Data Index: 523698 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9063. Min Act: -0.0001

Data Index: 270575 (C4 (Web Text))

Max Activating Token Index: 58