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

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

Neuron 3244 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.4147. Min Act: -0.0001

Data Index: 971972 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.4260. Min Act: -0.0001

Data Index: 1246872 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.4128. Min Act: -0.0001

Data Index: 370695 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.4122. Min Act: -0.0001

Data Index: 469078 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3870. Min Act: -0.0001

Data Index: 290259 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3732. Min Act: -0.0000

Data Index: 247087 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3805. Min Act: -0.0001

Data Index: 847463 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3848. Min Act: -0.0000

Data Index: 407122 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3722. Min Act: -0.0001

Data Index: 40522 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3693. Min Act: -0.0000

Data Index: 939863 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3685. Min Act: -0.0001

Data Index: 104165 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3770. Min Act: -0.0001

Data Index: 314921 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3684. Min Act: -0.0000

Data Index: 321745 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3545. Min Act: -0.0000

Data Index: 119004 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1021797 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3368. Min Act: -0.0000

Data Index: 922927 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3431. Min Act: -0.0000

Data Index: 677734 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1008300 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3367. Min Act: -0.0001

Data Index: 462949 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.4260. Min Range: -0.4260

Max Act: 0.3384. Min Act: -0.0001

Data Index: 323044 (C4 (Web Text))

Max Activating Token Index: 775