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

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

Neuron 3838 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: 6.4017. Min Range: -6.4017

Max Act: 6.4017. Min Act: -0.0000

Data Index: 1471416 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.1611. Min Act: -0.0000

Data Index: 1363876 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.3248. Min Act: -0.0000

Data Index: 1655652 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.3055. Min Act: -0.0000

Data Index: 1430476 (Python Code)

Max Activating Token Index: 615

Text #4

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.1164. Min Act: -0.0000

Data Index: 1374742 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.0936. Min Act: -0.0000

Data Index: 1598987 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.2660. Min Act: -0.0000

Data Index: 1362582 (Python Code)

Max Activating Token Index: 412

Text #7

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.8935. Min Act: -0.0000

Data Index: 1650886 (Python Code)

Max Activating Token Index: 687

Text #8

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.9912. Min Act: -0.0000

Data Index: 1360598 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.9450. Min Act: -0.0000

Data Index: 1378516 (Python Code)

Max Activating Token Index: 273

Text #10

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.1253. Min Act: -0.0000

Data Index: 1515125 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.6982. Min Act: -0.0000

Data Index: 1470336 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 6.4017. Min Range: -6.4017

Max Act: 6.0220. Min Act: -0.0000

Data Index: 1512925 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.8493. Min Act: -0.0000

Data Index: 1512307 (Python Code)

Max Activating Token Index: 781

Text #14

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.8798. Min Act: -0.0000

Data Index: 1644046 (Python Code)

Max Activating Token Index: 497

Text #15

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.7987. Min Act: -0.0000

Data Index: 1559176 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.8043. Min Act: -0.0000

Data Index: 1633599 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.9262. Min Act: -0.0000

Data Index: 1649079 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.7114. Min Act: -0.0000

Data Index: 1453851 (Python Code)

Max Activating Token Index: 361

Text #19

Max Range: 6.4017. Min Range: -6.4017

Max Act: 5.9356. Min Act: -0.0000

Data Index: 1513202 (Python Code)

Max Activating Token Index: 631