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

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

Neuron 3010 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1955. Min Range: -2.1955

Max Act: 2.1955. Min Act: -0.0000

Data Index: 1536239 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 2.1955. Min Range: -2.1955

Max Act: 2.0565. Min Act: -0.0000

Data Index: 1459634 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.9369. Min Act: -0.0000

Data Index: 1120253 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.8195. Min Act: -0.0000

Data Index: 512503 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.8967. Min Act: -0.0001

Data Index: 1043771 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.7979. Min Act: -0.0000

Data Index: 1551710 (Python Code)

Max Activating Token Index: 836

Text #6

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.9119. Min Act: -0.0000

Data Index: 887380 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.8064. Min Act: -0.0000

Data Index: 507882 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.8040. Min Act: -0.0001

Data Index: 1471522 (Python Code)

Max Activating Token Index: 639

Text #9

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6227. Min Act: -0.0000

Data Index: 689916 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6040. Min Act: -0.0000

Data Index: 1421017 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6908. Min Act: -0.0001

Data Index: 643319 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6917. Min Act: -0.0000

Data Index: 1571353 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6750. Min Act: -0.0000

Data Index: 203062 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.5868. Min Act: -0.0000

Data Index: 109749 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6657. Min Act: -0.0000

Data Index: 1493439 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6514. Min Act: -0.0000

Data Index: 1106150 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.7155. Min Act: -0.0000

Data Index: 430251 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.6397. Min Act: -0.0000

Data Index: 1297625 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 2.1955. Min Range: -2.1955

Max Act: 1.7134. Min Act: -0.0000

Data Index: 1088799 (C4 (Web Text))

Max Activating Token Index: 293