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

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

Neuron 2540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5225. Min Act: 0.0000

Data Index: 1172339 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4943. Min Act: -0.0000

Data Index: 247928 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4911. Min Act: -0.0000

Data Index: 24686 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5017. Min Act: -0.0000

Data Index: 872622 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4672. Min Act: -0.0000

Data Index: 266825 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4465. Min Act: -0.0000

Data Index: 620567 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4388. Min Act: 0.0000

Data Index: 416983 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4387. Min Act: -0.0000

Data Index: 41058 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4369. Min Act: -0.0000

Data Index: 786260 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4121. Min Act: -0.0000

Data Index: 641916 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4130. Min Act: -0.0000

Data Index: 973786 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4549. Min Act: -0.0000

Data Index: 206398 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1083427 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4185. Min Act: -0.0000

Data Index: 409520 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1198717 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4145. Min Act: -0.0000

Data Index: 699639 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1112897 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4063. Min Act: -0.0000

Data Index: 268295 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4008. Min Act: -0.0000

Data Index: 17048 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3934. Min Act: -0.0000

Data Index: 661604 (C4 (Web Text))

Max Activating Token Index: 481