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

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

Neuron 356 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.9627. Min Act: -0.0000

Data Index: 205694 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.9382. Min Act: -0.0000

Data Index: 968563 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8402. Min Act: -0.0000

Data Index: 357917 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1075981 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8073. Min Act: -0.0000

Data Index: 885239 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8452. Min Act: -0.0001

Data Index: 551102 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8836. Min Act: -0.0000

Data Index: 433633 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8411. Min Act: -0.0000

Data Index: 575250 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8136. Min Act: -0.0000

Data Index: 175648 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1150692 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8221. Min Act: -0.0000

Data Index: 934017 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7806. Min Act: -0.0001

Data Index: 928130 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7745. Min Act: -0.0001

Data Index: 827047 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7670. Min Act: -0.0000

Data Index: 554816 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8340. Min Act: -0.0000

Data Index: 557214 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8054. Min Act: -0.0000

Data Index: 231934 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7051. Min Act: -0.0001

Data Index: 288929 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7426. Min Act: -0.0000

Data Index: 22343 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7122. Min Act: -0.0001

Data Index: 101783 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1279620 (C4 (Web Text))

Max Activating Token Index: 177