Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 56 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.8142. Min Act: -0.0000

Data Index: 991697 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6405. Min Act: -0.0000

Data Index: 572005 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.5309. Min Act: -0.0000

Data Index: 975922 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4838. Min Act: -0.0000

Data Index: 486857 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1378764 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4525. Min Act: -0.0000

Data Index: 334000 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4552. Min Act: -0.0000

Data Index: 705548 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1472224 (Python Code)

Max Activating Token Index: 653

Text #8

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4409. Min Act: -0.0000

Data Index: 444579 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1426057 (Python Code)

Max Activating Token Index: 338

Text #10

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1511749 (Python Code)

Max Activating Token Index: 592

Text #11

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4076. Min Act: -0.0000

Data Index: 924755 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4237. Min Act: -0.0000

Data Index: 956894 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4178. Min Act: -0.0000

Data Index: 220458 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4210. Min Act: -0.0000

Data Index: 80300 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.3969. Min Act: -0.0000

Data Index: 96171 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1038293 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.3889. Min Act: -0.0000

Data Index: 374289 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1023477 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.4029. Min Act: -0.0000

Data Index: 381747 (C4 (Web Text))

Max Activating Token Index: 277