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

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

Neuron 220 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0002

Data Index: 713569 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0619. Min Act: -0.0002

Data Index: 165369 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0568. Min Act: -0.0003

Data Index: 41220 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0536. Min Act: -0.0002

Data Index: 974315 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0543. Min Act: -0.0002

Data Index: 96316 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0529. Min Act: -0.0003

Data Index: 685922 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0541. Min Act: -0.0002

Data Index: 891020 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0519. Min Act: -0.0002

Data Index: 583312 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1328086 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1348870 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0481. Min Act: -0.0002

Data Index: 601447 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0494. Min Act: -0.0002

Data Index: 876968 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1121962 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0483. Min Act: -0.0002

Data Index: 140534 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0462. Min Act: -0.0003

Data Index: 320652 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0469. Min Act: -0.0003

Data Index: 54906 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0466. Min Act: -0.0003

Data Index: 678094 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0454. Min Act: -0.0003

Data Index: 551715 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1123140 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0453. Min Act: -0.0002

Data Index: 236862 (C4 (Web Text))

Max Activating Token Index: 848