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

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

Neuron 4655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.9227. Min Act: -0.0000

Data Index: 813719 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7719. Min Act: -0.0000

Data Index: 82318 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7121. Min Act: -0.0000

Data Index: 165235 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7057. Min Act: -0.0000

Data Index: 262681 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1324812 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6897. Min Act: -0.0000

Data Index: 468655 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6587. Min Act: -0.0000

Data Index: 518623 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6521. Min Act: -0.0000

Data Index: 541171 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6677. Min Act: -0.0000

Data Index: 407036 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6701. Min Act: -0.0000

Data Index: 968605 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6436. Min Act: -0.0000

Data Index: 867439 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6535. Min Act: -0.0000

Data Index: 22894 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1082324 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6520. Min Act: -0.0000

Data Index: 270617 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1049348 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1345806 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6303. Min Act: -0.0000

Data Index: 631088 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1318791 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6292. Min Act: -0.0000

Data Index: 89703 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6431. Min Act: -0.0000

Data Index: 911416 (C4 (Web Text))

Max Activating Token Index: 136