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

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

Neuron 372 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: 2.1839. Min Range: -2.1839

Max Act: 2.1839. Min Act: -0.0001

Data Index: 330463 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.9306. Min Act: -0.0000

Data Index: 600122 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.8110. Min Act: -0.0001

Data Index: 491670 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.5516. Min Act: -0.0000

Data Index: 104247 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.5271. Min Act: -0.0000

Data Index: 613696 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.5067. Min Act: -0.0001

Data Index: 890781 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1307634 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.3598. Min Act: -0.0000

Data Index: 278890 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1007246 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.4160. Min Act: -0.0001

Data Index: 616944 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2962. Min Act: -0.0001

Data Index: 846021 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.3378. Min Act: -0.0000

Data Index: 697863 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2898. Min Act: -0.0001

Data Index: 1210670 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2566. Min Act: -0.0000

Data Index: 334247 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2447. Min Act: -0.0001

Data Index: 1319436 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2409. Min Act: -0.0000

Data Index: 304953 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2658. Min Act: -0.0000

Data Index: 906308 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2270. Min Act: -0.0001

Data Index: 957303 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2511. Min Act: -0.0000

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 2.1839. Min Range: -2.1839

Max Act: 1.2098. Min Act: -0.0000

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 40