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

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

Neuron 99 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1524512 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1555814 (Python Code)

Max Activating Token Index: 706

Text #2

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1426226 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1627974 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1367487 (Python Code)

Max Activating Token Index: 337

Text #5

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2077. Min Act: -0.0001

Data Index: 1403667 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1575524 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1373625 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1420303 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2036. Min Act: -0.0001

Data Index: 1452725 (Python Code)

Max Activating Token Index: 444

Text #10

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1370621 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2065. Min Act: -0.0001

Data Index: 1588533 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2035. Min Act: -0.0001

Data Index: 1545987 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1417711 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1362504 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2070. Min Act: -0.0001

Data Index: 1579222 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1472466 (Python Code)

Max Activating Token Index: 849

Text #17

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1612958 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1656628 (Python Code)

Max Activating Token Index: 961

Text #19

Max Range: 0.2455. Min Range: -0.2455

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1429580 (Python Code)

Max Activating Token Index: 895