Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2816 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.4728. Min Act: -0.0001

Data Index: 1509154 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.5066. Min Act: -0.0001

Data Index: 1501139 (Python Code)

Max Activating Token Index: 279

Text #2

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1434978 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3428. Min Act: -0.0001

Data Index: 1393541 (Python Code)

Max Activating Token Index: 996

Text #4

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3074. Min Act: -0.0001

Data Index: 1481449 (Python Code)

Max Activating Token Index: 376

Text #5

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3342. Min Act: -0.0001

Data Index: 1607471 (Python Code)

Max Activating Token Index: 126

Text #6

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1567220 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3059. Min Act: -0.0001

Data Index: 1432619 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1367044 (Python Code)

Max Activating Token Index: 1013

Text #9

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2845. Min Act: -0.0001

Data Index: 1511944 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2586. Min Act: -0.0001

Data Index: 1584202 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2862. Min Act: -0.0001

Data Index: 1552931 (Python Code)

Max Activating Token Index: 371

Text #12

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2885. Min Act: -0.0001

Data Index: 1529213 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2388. Min Act: -0.0001

Data Index: 1594924 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.1682. Min Act: -0.0001

Data Index: 1432000 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2392. Min Act: -0.0001

Data Index: 1437442 (Python Code)

Max Activating Token Index: 627

Text #16

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2381. Min Act: -0.0001

Data Index: 1512598 (Python Code)

Max Activating Token Index: 202

Text #17

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.1990. Min Act: -0.0001

Data Index: 1579888 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2287. Min Act: -0.0001

Data Index: 1392916 (Python Code)

Max Activating Token Index: 36

Text #19

Max Range: 1.5066. Min Range: -1.5066

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1393129 (Python Code)

Max Activating Token Index: 400