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

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

Neuron 2038 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1615562 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1409111 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1443779 (Python Code)

Max Activating Token Index: 630

Text #3

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1484508 (Python Code)

Max Activating Token Index: 513

Text #4

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1556192 (Python Code)

Max Activating Token Index: 765

Text #5

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1383141 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1516403 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1587046 (Python Code)

Max Activating Token Index: 600

Text #8

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1544983 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1393555 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1483716 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1377669 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1568974 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1360080 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5467. Min Act: -0.0000

Data Index: 282983 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1450228 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1494816 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1610565 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1514320 (Python Code)

Max Activating Token Index: 903

Text #19

Max Range: 0.7085. Min Range: -0.7085

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1393740 (Python Code)

Max Activating Token Index: 913