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

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

Neuron 3830 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.7116. Min Act: -0.0001

Data Index: 1442483 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.6093. Min Act: -0.0001

Data Index: 1559993 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5142. Min Act: -0.0001

Data Index: 1573955 (Python Code)

Max Activating Token Index: 779

Text #3

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5191. Min Act: -0.0001

Data Index: 1574048 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5065. Min Act: -0.0001

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.5047. Min Act: -0.0001

Data Index: 1513196 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3292. Min Act: -0.0001

Data Index: 1504577 (Python Code)

Max Activating Token Index: 595

Text #7

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4313. Min Act: -0.0001

Data Index: 1105221 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4708. Min Act: -0.0001

Data Index: 678250 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4919. Min Act: -0.0001

Data Index: 1391387 (Python Code)

Max Activating Token Index: 755

Text #10

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3851. Min Act: -0.0001

Data Index: 1517232 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.2863. Min Act: -0.0001

Data Index: 1407519 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3623. Min Act: -0.0001

Data Index: 1432427 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3106. Min Act: -0.0001

Data Index: 1565006 (Python Code)

Max Activating Token Index: 899

Text #14

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3574. Min Act: -0.0001

Data Index: 1400936 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3471. Min Act: -0.0001

Data Index: 1543332 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3791. Min Act: -0.0001

Data Index: 919051 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3118. Min Act: -0.0001

Data Index: 1617656 (Python Code)

Max Activating Token Index: 341

Text #18

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.4229. Min Act: -0.0001

Data Index: 1404065 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 1.7116. Min Range: -1.7116

Max Act: 1.3824. Min Act: -0.0001

Data Index: 1643910 (Python Code)

Max Activating Token Index: 132