Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2008 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0003

Data Index: 785389 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1111244 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0328. Min Act: -0.0003

Data Index: 420837 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0361. Min Act: -0.0004

Data Index: 733703 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0376. Min Act: -0.0003

Data Index: 581337 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0360. Min Act: -0.0004

Data Index: 409628 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1309112 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0351. Min Act: -0.0003

Data Index: 434548 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0335. Min Act: -0.0003

Data Index: 857862 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0325. Min Act: -0.0003

Data Index: 467544 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0334. Min Act: -0.0003

Data Index: 207662 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0348. Min Act: -0.0003

Data Index: 672548 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1098755 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0356. Min Act: -0.0003

Data Index: 996937 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0359. Min Act: -0.0003

Data Index: 854933 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0343. Min Act: -0.0003

Data Index: 281391 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0348. Min Act: -0.0003

Data Index: 582351 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0328. Min Act: -0.0003

Data Index: 907396 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1337833 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1034110 (C4 (Web Text))

Max Activating Token Index: 374