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

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

Neuron 5551 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3221. Min Range: -2.3221

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1540429 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 2.3221. Min Range: -2.3221

Max Act: 2.1596. Min Act: -0.0000

Data Index: 1253085 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1635994 (Python Code)

Max Activating Token Index: 936

Text #3

Max Range: 2.3221. Min Range: -2.3221

Max Act: 2.0088. Min Act: -0.0000

Data Index: 1562456 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.8903. Min Act: -0.0000

Data Index: 1214931 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.8876. Min Act: -0.0000

Data Index: 298294 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.6997. Min Act: -0.0000

Data Index: 947426 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.6896. Min Act: -0.0000

Data Index: 1495374 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.5912. Min Act: -0.0000

Data Index: 67522 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.7371. Min Act: -0.0000

Data Index: 1336423 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.6430. Min Act: -0.0000

Data Index: 959384 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.5265. Min Act: -0.0000

Data Index: 591018 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.6738. Min Act: -0.0000

Data Index: 1640743 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.4961. Min Act: -0.0000

Data Index: 904938 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.5740. Min Act: -0.0000

Data Index: 16094 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.6644. Min Act: -0.0000

Data Index: 1447613 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.5550. Min Act: -0.0000

Data Index: 1523294 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.5533. Min Act: -0.0000

Data Index: 1148212 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.5473. Min Act: -0.0000

Data Index: 1526725 (Python Code)

Max Activating Token Index: 395

Text #19

Max Range: 2.3221. Min Range: -2.3221

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1107175 (C4 (Web Text))

Max Activating Token Index: 414