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

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

Neuron 2450 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: 0.7395. Min Range: -0.7395

Max Act: 0.7395. Min Act: -0.0002

Data Index: 73886 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.6876. Min Act: -0.0002

Data Index: 551189 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.6483. Min Act: -0.0003

Data Index: 579776 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.6087. Min Act: -0.0002

Data Index: 745058 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5471. Min Act: -0.0002

Data Index: 707019 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5377. Min Act: -0.0003

Data Index: 881128 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5237. Min Act: -0.0002

Data Index: 25045 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4961. Min Act: -0.0002

Data Index: 1036697 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4978. Min Act: -0.0002

Data Index: 1063884 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4779. Min Act: -0.0003

Data Index: 453785 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4840. Min Act: -0.0003

Data Index: 1318584 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4437. Min Act: -0.0002

Data Index: 909326 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4561. Min Act: -0.0002

Data Index: 308890 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4450. Min Act: -0.0002

Data Index: 919984 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4357. Min Act: -0.0002

Data Index: 1169 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4170. Min Act: -0.0002

Data Index: 444751 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4096. Min Act: -0.0003

Data Index: 423397 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3882. Min Act: -0.0003

Data Index: 892465 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3874. Min Act: -0.0003

Data Index: 1241298 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3866. Min Act: -0.0002

Data Index: 96972 (C4 (Web Text))

Max Activating Token Index: 209