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

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

Neuron 1712 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.0099. Min Act: -0.0001

Data Index: 1649737 (Python Code)

Max Activating Token Index: 815

Text #1

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.1346. Min Act: -0.0001

Data Index: 1576140 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.1346. Min Act: -0.0001

Data Index: 1567315 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.0153. Min Act: -0.0001

Data Index: 1440719 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.0218. Min Act: -0.0001

Data Index: 1481941 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.0814. Min Act: -0.0001

Data Index: 1228805 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.0856. Min Act: -0.0001

Data Index: 1517028 (Python Code)

Max Activating Token Index: 219

Text #7

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.9384. Min Act: -0.0001

Data Index: 256849 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 1.1346. Min Range: -1.1346

Max Act: 1.0107. Min Act: -0.0001

Data Index: 422161 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.9595. Min Act: -0.0001

Data Index: 1427041 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8926. Min Act: -0.0001

Data Index: 1579122 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.9669. Min Act: -0.0001

Data Index: 775183 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8977. Min Act: -0.0001

Data Index: 132858 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.9175. Min Act: -0.0001

Data Index: 1613392 (Python Code)

Max Activating Token Index: 596

Text #14

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8601. Min Act: -0.0001

Data Index: 1539036 (Python Code)

Max Activating Token Index: 80

Text #15

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8719. Min Act: -0.0001

Data Index: 1588381 (Python Code)

Max Activating Token Index: 967

Text #16

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1441212 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8102. Min Act: -0.0001

Data Index: 1538194 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8503. Min Act: -0.0001

Data Index: 1574167 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 1.1346. Min Range: -1.1346

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1590208 (Python Code)

Max Activating Token Index: 600