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

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

Neuron 119 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: 1.5021. Min Range: -1.5021

Max Act: 1.5021. Min Act: -0.0001

Data Index: 660612 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.3421. Min Act: -0.0001

Data Index: 1131138 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.4448. Min Act: -0.0001

Data Index: 654970 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.3219. Min Act: -0.0001

Data Index: 1197057 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.3270. Min Act: -0.0001

Data Index: 472656 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.2411. Min Act: -0.0001

Data Index: 1062809 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.2782. Min Act: -0.0001

Data Index: 1301271 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1779. Min Act: -0.0001

Data Index: 1278521 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1415. Min Act: -0.0001

Data Index: 193181 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.2306. Min Act: -0.0001

Data Index: 691557 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1861. Min Act: -0.0001

Data Index: 894593 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1399. Min Act: -0.0001

Data Index: 91148 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1976. Min Act: -0.0001

Data Index: 1196987 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1597. Min Act: -0.0001

Data Index: 366323 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.2068. Min Act: -0.0001

Data Index: 1033324 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1388. Min Act: -0.0001

Data Index: 90930 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1942. Min Act: -0.0001

Data Index: 246655 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1047. Min Act: -0.0001

Data Index: 210097 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.0298. Min Act: -0.0001

Data Index: 528270 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 1.5021. Min Range: -1.5021

Max Act: 1.1031. Min Act: -0.0001

Data Index: 1100365 (C4 (Web Text))

Max Activating Token Index: 182