Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 475 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.3059. Min Act: -0.0003

Data Index: 1493014 (Python Code)

Max Activating Token Index: 641

Text #1

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.2142. Min Act: -0.0003

Data Index: 1365312 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.2346. Min Act: -0.0003

Data Index: 1361725 (Python Code)

Max Activating Token Index: 439

Text #3

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1745. Min Act: -0.0003

Data Index: 1517388 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.2605. Min Act: -0.0004

Data Index: 1422331 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0710. Min Act: -0.0003

Data Index: 1618088 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1966. Min Act: -0.0003

Data Index: 1505221 (Python Code)

Max Activating Token Index: 799

Text #7

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1651. Min Act: -0.0003

Data Index: 1464367 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1247. Min Act: -0.0003

Data Index: 1652156 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1574. Min Act: -0.0003

Data Index: 1428015 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0828. Min Act: -0.0003

Data Index: 1502806 (Python Code)

Max Activating Token Index: 983

Text #11

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0779. Min Act: -0.0003

Data Index: 1481105 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0780. Min Act: -0.0004

Data Index: 1534489 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0711. Min Act: -0.0003

Data Index: 1458587 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1160. Min Act: -0.0003

Data Index: 1467055 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0866. Min Act: -0.0003

Data Index: 1490265 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1168. Min Act: -0.0003

Data Index: 1614323 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0725. Min Act: -0.0004

Data Index: 1550361 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0941. Min Act: -0.0003

Data Index: 1634527 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0955. Min Act: -0.0003

Data Index: 1581637 (Python Code)

Max Activating Token Index: 688