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

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

Neuron 5177 in Layer 1

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: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1551154 (Python Code)

Max Activating Token Index: 239

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1446944 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1542822 (Python Code)

Max Activating Token Index: 185

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1389035 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1071. Min Act: -0.0002

Data Index: 254020 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1510546 (Python Code)

Max Activating Token Index: 971

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1495787 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1375180 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1062. Min Act: -0.0002

Data Index: 472140 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1481374 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1433056 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1452039 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1641271 (Python Code)

Max Activating Token Index: 154

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1394750 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1616159 (Python Code)

Max Activating Token Index: 243

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1635122 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1509594 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1363035 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1613656 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1381667 (Python Code)

Max Activating Token Index: 59