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

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

Neuron 2155 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1253. Min Range: -3.1253

Max Act: 3.1253. Min Act: -0.0000

Data Index: 1174040 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.8102. Min Act: -0.0000

Data Index: 408574 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.6930. Min Act: -0.0000

Data Index: 1467079 (Python Code)

Max Activating Token Index: 650

Text #3

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.7322. Min Act: -0.0000

Data Index: 368629 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1655513 (Python Code)

Max Activating Token Index: 696

Text #5

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1606185 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1574636 (Python Code)

Max Activating Token Index: 805

Text #7

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.5837. Min Act: -0.0000

Data Index: 103870 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.5919. Min Act: -0.0000

Data Index: 229958 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1458219 (Python Code)

Max Activating Token Index: 895

Text #10

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1222128 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.6001. Min Act: -0.0000

Data Index: 1590531 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1488590 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1233614 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.4878. Min Act: -0.0000

Data Index: 989305 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.4159. Min Act: -0.0000

Data Index: 841556 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.2042. Min Act: -0.0000

Data Index: 152278 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.4022. Min Act: -0.0000

Data Index: 418973 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1156799 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 3.1253. Min Range: -3.1253

Max Act: 1.3018. Min Act: -0.0000

Data Index: 782544 (C4 (Web Text))

Max Activating Token Index: 503