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

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

Neuron 505 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.6700. Min Act: -0.0000

Data Index: 860398 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.6548. Min Act: -0.0000

Data Index: 367725 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.3920. Min Act: -0.0000

Data Index: 576094 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.3803. Min Act: -0.0000

Data Index: 209524 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.3115. Min Act: -0.0000

Data Index: 228989 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.2614. Min Act: -0.0000

Data Index: 554541 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.1868. Min Act: -0.0000

Data Index: 687274 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.2202. Min Act: -0.0000

Data Index: 761520 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1135716 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.2135. Min Act: -0.0000

Data Index: 615667 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.1981. Min Act: -0.0000

Data Index: 246291 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.2289. Min Act: -0.0000

Data Index: 856211 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.1500. Min Act: -0.0000

Data Index: 966 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1113826 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.0828. Min Act: -0.0000

Data Index: 30782 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 1.6700. Min Range: -1.6700

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1137887 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.0418. Min Act: -0.0000

Data Index: 593024 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1301385 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.1339. Min Act: -0.0000

Data Index: 487177 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.6700. Min Range: -1.6700

Max Act: 1.0813. Min Act: -0.0000

Data Index: 604539 (C4 (Web Text))

Max Activating Token Index: 555