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

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

Neuron 3989 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: 1.6769. Min Range: -1.6769

Max Act: 1.2610. Min Act: -0.0002

Data Index: 1605719 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.5387. Min Act: -0.0002

Data Index: 1581760 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.4531. Min Act: -0.0002

Data Index: 1466230 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.2079. Min Act: -0.0002

Data Index: 1475079 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.6090. Min Act: -0.0002

Data Index: 1472276 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.1124. Min Act: -0.0002

Data Index: 1372305 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.4303. Min Act: -0.0002

Data Index: 1521174 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.3977. Min Act: -0.0002

Data Index: 1571108 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.5733. Min Act: -0.0002

Data Index: 1393248 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.6382. Min Act: -0.0002

Data Index: 1427253 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.3420. Min Act: -0.0002

Data Index: 1574209 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.3420. Min Act: -0.0002

Data Index: 1440346 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.4066. Min Act: -0.0002

Data Index: 1359881 (Python Code)

Max Activating Token Index: 299

Text #13

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.4507. Min Act: -0.0002

Data Index: 1400592 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.2287. Min Act: -0.0002

Data Index: 1615113 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.4356. Min Act: -0.0002

Data Index: 1599238 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.2551. Min Act: -0.0002

Data Index: 1591696 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.6769. Min Act: -0.0002

Data Index: 1387345 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.2030. Min Act: -0.0002

Data Index: 1484409 (Python Code)

Max Activating Token Index: 276

Text #19

Max Range: 1.6769. Min Range: -1.6769

Max Act: 1.3379. Min Act: -0.0002

Data Index: 1416472 (Python Code)

Max Activating Token Index: 606