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

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

Neuron 3019 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6726. Min Act: -0.0001

Data Index: 329119 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.5822. Min Act: -0.0001

Data Index: 443490 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.5556. Min Act: -0.0001

Data Index: 134382 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.5090. Min Act: -0.0001

Data Index: 793622 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.5006. Min Act: -0.0001

Data Index: 721937 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4434. Min Act: -0.0001

Data Index: 243424 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4384. Min Act: -0.0001

Data Index: 897692 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4196. Min Act: -0.0001

Data Index: 1005725 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4025. Min Act: -0.0001

Data Index: 560633 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.3728. Min Act: -0.0001

Data Index: 897825 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4331. Min Act: -0.0001

Data Index: 50326 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.3809. Min Act: -0.0001

Data Index: 772227 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4079. Min Act: -0.0001

Data Index: 1020899 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.3740. Min Act: -0.0001

Data Index: 513137 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4092. Min Act: -0.0001

Data Index: 1177501 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4192. Min Act: -0.0001

Data Index: 425634 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.4010. Min Act: -0.0001

Data Index: 513113 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.3635. Min Act: -0.0001

Data Index: 773528 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.3762. Min Act: -0.0001

Data Index: 396491 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.3947. Min Act: -0.0001

Data Index: 124873 (C4 (Web Text))

Max Activating Token Index: 286