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

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

Neuron 1005 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5593. Min Act: -0.0000

Data Index: 414505 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5077. Min Act: -0.0000

Data Index: 808547 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4931. Min Act: -0.0001

Data Index: 1088000 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1272228 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1329565 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1078630 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4469. Min Act: -0.0000

Data Index: 602816 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4563. Min Act: -0.0001

Data Index: 112616 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4354. Min Act: -0.0000

Data Index: 785691 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4490. Min Act: -0.0000

Data Index: 38447 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1220508 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4200. Min Act: -0.0001

Data Index: 626638 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4246. Min Act: -0.0000

Data Index: 849380 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1300378 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4168. Min Act: -0.0000

Data Index: 184385 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4454. Min Act: -0.0000

Data Index: 40186 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4305. Min Act: -0.0000

Data Index: 890692 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3882. Min Act: -0.0001

Data Index: 422750 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4400. Min Act: -0.0000

Data Index: 706623 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4230. Min Act: -0.0000

Data Index: 267298 (C4 (Web Text))

Max Activating Token Index: 165