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

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

Neuron 1984 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2634. Min Act: -0.0000

Data Index: 874576 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.4206. Min Act: -0.0000

Data Index: 1584407 (Python Code)

Max Activating Token Index: 856

Text #2

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1518814 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1651512 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1635893 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.1115. Min Act: -0.0000

Data Index: 378031 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1574709 (Python Code)

Max Activating Token Index: 852

Text #7

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1485529 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2189. Min Act: -0.0000

Data Index: 398704 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1466335 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1565393 (Python Code)

Max Activating Token Index: 229

Text #11

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1537816 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2251. Min Act: -0.0000

Data Index: 1583453 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.0217. Min Act: -0.0000

Data Index: 784226 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.0575. Min Act: -0.0000

Data Index: 76301 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1527969 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1554626 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.0207. Min Act: -0.0000

Data Index: 1565578 (Python Code)

Max Activating Token Index: 649

Text #18

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1612450 (Python Code)

Max Activating Token Index: 401

Text #19

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.1954. Min Act: -0.0000

Data Index: 1416504 (Python Code)

Max Activating Token Index: 970