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

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

Neuron 2624 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: 0.7085. Min Range: -0.7085

Max Act: 0.7085. Min Act: -0.0000

Data Index: 253961 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5695. Min Act: -0.0000

Data Index: 250710 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5247. Min Act: -0.0000

Data Index: 301269 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5093. Min Act: -0.0000

Data Index: 604250 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1212223 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5140. Min Act: -0.0000

Data Index: 680268 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1210730 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4868. Min Act: -0.0000

Data Index: 66339 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5053. Min Act: -0.0000

Data Index: 527751 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4671. Min Act: -0.0000

Data Index: 687214 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4430. Min Act: -0.0000

Data Index: 645866 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4302. Min Act: -0.0000

Data Index: 813403 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4442. Min Act: -0.0000

Data Index: 460487 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4431. Min Act: -0.0000

Data Index: 99410 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4352. Min Act: -0.0000

Data Index: 568754 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4365. Min Act: -0.0000

Data Index: 627147 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4354. Min Act: -0.0000

Data Index: 164122 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4200. Min Act: -0.0000

Data Index: 190129 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4583. Min Act: -0.0000

Data Index: 170165 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.4176. Min Act: -0.0000

Data Index: 114479 (C4 (Web Text))

Max Activating Token Index: 897