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

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

Neuron 3780 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: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0003

Data Index: 425196 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0378. Min Act: -0.0002

Data Index: 834084 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1039618 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0367. Min Act: -0.0003

Data Index: 362104 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0355. Min Act: -0.0003

Data Index: 140084 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0364. Min Act: -0.0003

Data Index: 113836 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1258603 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1014258 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0353. Min Act: -0.0003

Data Index: 784365 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0351. Min Act: -0.0003

Data Index: 105497 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0346. Min Act: -0.0003

Data Index: 704881 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0342. Min Act: -0.0003

Data Index: 172593 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0347. Min Act: -0.0003

Data Index: 485947 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0345. Min Act: -0.0003

Data Index: 917420 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0344. Min Act: -0.0002

Data Index: 924323 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1512570 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1269969 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0330. Min Act: -0.0003

Data Index: 40012 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1257719 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0311. Min Act: -0.0002

Data Index: 845721 (C4 (Web Text))

Max Activating Token Index: 1013