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

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

Neuron 4224 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0459. Min Range: -2.0459

Max Act: 2.0459. Min Act: -0.0000

Data Index: 883870 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.9130. Min Act: -0.0000

Data Index: 585687 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.8884. Min Act: -0.0000

Data Index: 1309708 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.7292. Min Act: -0.0000

Data Index: 1098623 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.7126. Min Act: -0.0000

Data Index: 1200087 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1102813 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1347795 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.4484. Min Act: -0.0000

Data Index: 1073660 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.3624. Min Act: -0.0000

Data Index: 574971 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.3855. Min Act: -0.0000

Data Index: 26122 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1289537 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.3724. Min Act: -0.0000

Data Index: 852820 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.3872. Min Act: -0.0000

Data Index: 405316 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.2485. Min Act: -0.0000

Data Index: 405792 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1330375 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1287458 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.2544. Min Act: -0.0000

Data Index: 72472 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.2105. Min Act: -0.0000

Data Index: 487032 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.1589. Min Act: 0.0000

Data Index: 403144 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 2.0459. Min Range: -2.0459

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1298508 (C4 (Web Text))

Max Activating Token Index: 689