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

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

Neuron 5039 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.8154. Min Act: -0.0000

Data Index: 1552345 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.6143. Min Act: -0.0000

Data Index: 1478783 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.7969. Min Act: -0.0000

Data Index: 1635204 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.6006. Min Act: -0.0000

Data Index: 1550191 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1627830 (Python Code)

Max Activating Token Index: 423

Text #5

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.5783. Min Act: -0.0000

Data Index: 1580844 (Python Code)

Max Activating Token Index: 656

Text #6

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1495919 (Python Code)

Max Activating Token Index: 331

Text #7

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1498122 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1555618 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1529610 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4840. Min Act: -0.0000

Data Index: 1424381 (Python Code)

Max Activating Token Index: 639

Text #11

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1623910 (Python Code)

Max Activating Token Index: 199

Text #12

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4593. Min Act: -0.0000

Data Index: 1656747 (Python Code)

Max Activating Token Index: 332

Text #13

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4464. Min Act: -0.0000

Data Index: 1428047 (Python Code)

Max Activating Token Index: 346

Text #14

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1393694 (Python Code)

Max Activating Token Index: 400

Text #15

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1451490 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4126. Min Act: -0.0000

Data Index: 1625529 (Python Code)

Max Activating Token Index: 779

Text #17

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1575037 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1458257 (Python Code)

Max Activating Token Index: 465

Text #19

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1487936 (Python Code)

Max Activating Token Index: 509