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

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

Neuron 2526 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3971. Min Range: -2.3971

Max Act: 2.3788. Min Act: -0.0000

Data Index: 568958 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 2.3971. Min Range: -2.3971

Max Act: 2.3971. Min Act: -0.0000

Data Index: 1119855 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.9690. Min Act: -0.0000

Data Index: 748845 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.9288. Min Act: -0.0000

Data Index: 350457 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.7354. Min Act: -0.0000

Data Index: 42942 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.6902. Min Act: -0.0000

Data Index: 336096 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.5127. Min Act: -0.0000

Data Index: 840099 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.4116. Min Act: -0.0000

Data Index: 162113 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2851. Min Act: -0.0000

Data Index: 802264 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2838. Min Act: -0.0000

Data Index: 341528 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2659. Min Act: -0.0000

Data Index: 840943 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2576. Min Act: -0.0000

Data Index: 875517 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.1916. Min Act: -0.0000

Data Index: 11857 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1163521 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.3236. Min Act: -0.0000

Data Index: 818050 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.3129. Min Act: -0.0000

Data Index: 328007 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2208. Min Act: -0.0000

Data Index: 246150 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2164. Min Act: -0.0000

Data Index: 319881 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1257651 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 2.3971. Min Range: -2.3971

Max Act: 1.1700. Min Act: -0.0000

Data Index: 27328 (C4 (Web Text))

Max Activating Token Index: 74