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

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

Neuron 4607 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2630. Min Act: -0.0001

Data Index: 392865 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.4033. Min Act: -0.0001

Data Index: 914705 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.4018. Min Act: -0.0001

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2438. Min Act: -0.0001

Data Index: 82803 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2845. Min Act: -0.0001

Data Index: 706427 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.3064. Min Act: -0.0001

Data Index: 578335 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.3075. Min Act: -0.0001

Data Index: 163110 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.3705. Min Act: -0.0001

Data Index: 248138 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.1817. Min Act: -0.0001

Data Index: 66379 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.1714. Min Act: -0.0001

Data Index: 402515 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.4377. Min Act: -0.0001

Data Index: 433569 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.3180. Min Act: -0.0001

Data Index: 1143037 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.3189. Min Act: -0.0001

Data Index: 183445 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2727. Min Act: -0.0001

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2361. Min Act: -0.0001

Data Index: 331561 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2639. Min Act: -0.0001

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.1436. Min Act: -0.0001

Data Index: 235452 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2595. Min Act: -0.0001

Data Index: 1036818 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.1596. Min Act: -0.0001

Data Index: 881252 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 1.4377. Min Range: -1.4377

Max Act: 1.2191. Min Act: -0.0001

Data Index: 720297 (C4 (Web Text))

Max Activating Token Index: 102