Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2429 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.5381. Min Act: -0.0001

Data Index: 754273 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.5067. Min Act: -0.0001

Data Index: 905561 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.5377. Min Act: -0.0001

Data Index: 324843 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4999. Min Act: -0.0001

Data Index: 758009 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4602. Min Act: -0.0001

Data Index: 155953 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4722. Min Act: -0.0001

Data Index: 219554 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4515. Min Act: -0.0001

Data Index: 912638 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4875. Min Act: -0.0001

Data Index: 154356 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4659. Min Act: -0.0001

Data Index: 848675 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4286. Min Act: -0.0001

Data Index: 416921 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4582. Min Act: -0.0001

Data Index: 349977 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4222. Min Act: -0.0001

Data Index: 1390766 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4368. Min Act: -0.0001

Data Index: 1135581 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4352. Min Act: -0.0001

Data Index: 105102 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4194. Min Act: -0.0001

Data Index: 936664 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4171. Min Act: -0.0001

Data Index: 450326 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3942. Min Act: -0.0001

Data Index: 512786 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4160. Min Act: -0.0001

Data Index: 954820 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4520. Min Act: -0.0001

Data Index: 75792 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4121. Min Act: -0.0001

Data Index: 171485 (C4 (Web Text))

Max Activating Token Index: 617