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

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

Neuron 4277 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.1325. Min Act: -0.0000

Data Index: 513463 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1576097 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1566170 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1366801 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1492772 (Python Code)

Max Activating Token Index: 437

Text #5

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.2183. Min Act: -0.0000

Data Index: 1587085 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1499241 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1556392 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1391489 (Python Code)

Max Activating Token Index: 513

Text #9

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1544146 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1562063 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1416188 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1459260 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8202. Min Act: -0.0000

Data Index: 127252 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1491508 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1371120 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8824. Min Act: -0.0000

Data Index: 753939 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1114405 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1633013 (Python Code)

Max Activating Token Index: 294

Text #19

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1370974 (Python Code)

Max Activating Token Index: 621