Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1950 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.1065. Min Act: -0.0000

Data Index: 1588246 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.4232. Min Act: -0.0001

Data Index: 1621877 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.2970. Min Act: -0.0001

Data Index: 1439555 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.4177. Min Act: -0.0001

Data Index: 1435321 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.2398. Min Act: -0.0000

Data Index: 1478424 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.2500. Min Act: -0.0001

Data Index: 1371501 (Python Code)

Max Activating Token Index: 708

Text #6

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.1610. Min Act: -0.0001

Data Index: 1582212 (Python Code)

Max Activating Token Index: 917

Text #7

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.2652. Min Act: -0.0001

Data Index: 1646281 (Python Code)

Max Activating Token Index: 565

Text #8

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.2661. Min Act: -0.0000

Data Index: 1453588 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.0675. Min Act: -0.0000

Data Index: 1545352 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.1228. Min Act: -0.0001

Data Index: 1649069 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.1182. Min Act: -0.0000

Data Index: 1510848 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.0225. Min Act: -0.0001

Data Index: 1561466 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.0240. Min Act: -0.0001

Data Index: 1614567 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 3.1065. Min Range: -3.1065

Max Act: 1.9099. Min Act: -0.0001

Data Index: 1601312 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 3.1065. Min Range: -3.1065

Max Act: 1.9037. Min Act: -0.0001

Data Index: 1413213 (Python Code)

Max Activating Token Index: 249

Text #16

Max Range: 3.1065. Min Range: -3.1065

Max Act: 1.9501. Min Act: -0.0001

Data Index: 1413912 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 3.1065. Min Range: -3.1065

Max Act: 1.9173. Min Act: -0.0001

Data Index: 1480706 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 3.1065. Min Range: -3.1065

Max Act: 1.7987. Min Act: -0.0001

Data Index: 1593136 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 3.1065. Min Range: -3.1065

Max Act: 1.8430. Min Act: -0.0001

Data Index: 1598299 (Python Code)

Max Activating Token Index: 432