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

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

Neuron 4850 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1491936 (Python Code)

Max Activating Token Index: 484

Text #1

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5934. Min Act: -0.0000

Data Index: 196199 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1650700 (Python Code)

Max Activating Token Index: 287

Text #3

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4503. Min Act: -0.0000

Data Index: 936864 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1395215 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4375. Min Act: -0.0000

Data Index: 916395 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1522938 (Python Code)

Max Activating Token Index: 817

Text #7

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1466513 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1363002 (Python Code)

Max Activating Token Index: 934

Text #9

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1494005 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1630831 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3440. Min Act: -0.0000

Data Index: 610798 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1571043 (Python Code)

Max Activating Token Index: 863

Text #13

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1544789 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1504165 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1603168 (Python Code)

Max Activating Token Index: 683

Text #16

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1459353 (Python Code)

Max Activating Token Index: 286

Text #17

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1654346 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1615131 (Python Code)

Max Activating Token Index: 676

Text #19

Max Range: 0.6012. Min Range: -0.6012

Max Act: 0.3513. Min Act: -0.0000

Data Index: 652979 (C4 (Web Text))

Max Activating Token Index: 491