Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2838. Min Act: -0.0001

Data Index: 1479667 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2696. Min Act: -0.0001

Data Index: 1647957 (Python Code)

Max Activating Token Index: 124

Text #2

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.4118. Min Act: -0.0001

Data Index: 1383417 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1367956 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1431756 (Python Code)

Max Activating Token Index: 659

Text #5

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1433148 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1653281 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1574423 (Python Code)

Max Activating Token Index: 117

Text #8

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1414695 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1534565 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1176. Min Act: -0.0001

Data Index: 1577248 (Python Code)

Max Activating Token Index: 401

Text #11

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1184. Min Act: -0.0001

Data Index: 1620878 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1410856 (Python Code)

Max Activating Token Index: 683

Text #13

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1519138 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1497329 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.0599. Min Act: -0.0001

Data Index: 1441918 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.0622. Min Act: -0.0000

Data Index: 1593673 (Python Code)

Max Activating Token Index: 447

Text #17

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.0173. Min Act: -0.0001

Data Index: 1594841 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 1.4118. Min Range: -1.4118

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1425364 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 1.4118. Min Range: -1.4118

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1386116 (Python Code)

Max Activating Token Index: 339