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

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

Neuron 286 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0551. Min Act: -0.0002

Data Index: 977052 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0549. Min Act: -0.0002

Data Index: 776782 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 339890 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0450. Min Act: -0.0002

Data Index: 155094 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0503. Min Act: -0.0002

Data Index: 578146 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0437. Min Act: -0.0002

Data Index: 761021 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0440. Min Act: -0.0002

Data Index: 320197 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0446. Min Act: -0.0002

Data Index: 940900 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1176225 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0401. Min Act: -0.0002

Data Index: 466951 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0416. Min Act: -0.0002

Data Index: 847588 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0424. Min Act: -0.0002

Data Index: 165662 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0420. Min Act: -0.0002

Data Index: 159844 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1355402 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1356085 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0401. Min Act: -0.0002

Data Index: 763467 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0419. Min Act: -0.0002

Data Index: 100104 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0431. Min Act: -0.0002

Data Index: 240496 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1114325 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0384. Min Act: -0.0002

Data Index: 515186 (C4 (Web Text))

Max Activating Token Index: 644