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

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

Neuron 5360 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1607154 (Python Code)

Max Activating Token Index: 277

Text #1

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1650826 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1517679 (Python Code)

Max Activating Token Index: 174

Text #3

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1414110 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1351. Min Act: -0.0000

Data Index: 42421 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1616255 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1528431 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1623889 (Python Code)

Max Activating Token Index: 595

Text #8

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1655181 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1335. Min Act: -0.0000

Data Index: 219035 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1413. Min Act: -0.0000

Data Index: 658863 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1635712 (Python Code)

Max Activating Token Index: 993

Text #12

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1314. Min Act: -0.0000

Data Index: 607562 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1594922 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1455399 (Python Code)

Max Activating Token Index: 730

Text #15

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1289. Min Act: -0.0000

Data Index: 206036 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1439146 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1340921 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1600263 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1117. Min Act: -0.0000

Data Index: 825996 (C4 (Web Text))

Max Activating Token Index: 158