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

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

Neuron 1456 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3561. Min Act: -0.0000

Data Index: 613056 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3049. Min Act: -0.0000

Data Index: 174814 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1324819 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1088252 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2682. Min Act: 0.0000

Data Index: 669077 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2667. Min Act: -0.0000

Data Index: 177157 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2612. Min Act: -0.0000

Data Index: 891213 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1101365 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2528. Min Act: -0.0000

Data Index: 869880 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2465. Min Act: 0.0000

Data Index: 999514 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2435. Min Act: -0.0000

Data Index: 485571 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2378. Min Act: -0.0000

Data Index: 676423 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1026747 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2319. Min Act: -0.0000

Data Index: 661554 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2338. Min Act: -0.0000

Data Index: 214606 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2414. Min Act: -0.0000

Data Index: 581551 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2274. Min Act: -0.0000

Data Index: 998258 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1247298 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1095697 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1067247 (C4 (Web Text))

Max Activating Token Index: 612