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

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

Neuron 4563 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: 1.2074. Min Range: -1.2074

Max Act: 0.9864. Min Act: -0.0001

Data Index: 1374041 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 1.2074. Min Range: -1.2074

Max Act: 1.2074. Min Act: -0.0001

Data Index: 1641475 (Python Code)

Max Activating Token Index: 652

Text #2

Max Range: 1.2074. Min Range: -1.2074

Max Act: 1.1421. Min Act: -0.0001

Data Index: 1543337 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.9895. Min Act: -0.0001

Data Index: 1465217 (Python Code)

Max Activating Token Index: 93

Text #4

Max Range: 1.2074. Min Range: -1.2074

Max Act: 1.0040. Min Act: -0.0001

Data Index: 1435188 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 1.2074. Min Range: -1.2074

Max Act: 1.0917. Min Act: -0.0001

Data Index: 1563187 (Python Code)

Max Activating Token Index: 605

Text #6

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1574499 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.8439. Min Act: -0.0001

Data Index: 925179 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.2074. Min Range: -1.2074

Max Act: 1.0496. Min Act: -0.0001

Data Index: 1409721 (Python Code)

Max Activating Token Index: 746

Text #9

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.9409. Min Act: -0.0001

Data Index: 1413742 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.9320. Min Act: -0.0001

Data Index: 1111259 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.8292. Min Act: -0.0001

Data Index: 1492779 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.8384. Min Act: -0.0001

Data Index: 1434015 (Python Code)

Max Activating Token Index: 203

Text #13

Max Range: 1.2074. Min Range: -1.2074

Max Act: 1.0113. Min Act: -0.0001

Data Index: 1549457 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.7162. Min Act: -0.0001

Data Index: 1412822 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.9290. Min Act: -0.0001

Data Index: 1475273 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1491934 (Python Code)

Max Activating Token Index: 702

Text #17

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.7640. Min Act: -0.0001

Data Index: 1642911 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.8622. Min Act: -0.0001

Data Index: 1426466 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1187438 (C4 (Web Text))

Max Activating Token Index: 594