Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2184 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.7174. Min Act: -0.0001

Data Index: 629070 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6800. Min Act: -0.0001

Data Index: 1163394 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6019. Min Act: -0.0001

Data Index: 459254 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6233. Min Act: -0.0001

Data Index: 921243 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5055. Min Act: -0.0001

Data Index: 738655 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6295. Min Act: -0.0001

Data Index: 521095 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5762. Min Act: -0.0001

Data Index: 22291 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5671. Min Act: -0.0001

Data Index: 568237 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5364. Min Act: -0.0001

Data Index: 753030 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6056. Min Act: -0.0001

Data Index: 532893 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5752. Min Act: -0.0001

Data Index: 310604 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5875. Min Act: -0.0001

Data Index: 1213986 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5678. Min Act: -0.0001

Data Index: 1225579 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5971. Min Act: -0.0001

Data Index: 1356590 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4875. Min Act: -0.0001

Data Index: 677999 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1195860 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5388. Min Act: -0.0001

Data Index: 57614 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5801. Min Act: -0.0001

Data Index: 202266 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5798. Min Act: -0.0001

Data Index: 559309 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5179. Min Act: -0.0001

Data Index: 355939 (C4 (Web Text))

Max Activating Token Index: 320