Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4850 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.6116. Min Act: -0.0000

Data Index: 438074 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3945. Min Act: -0.0000

Data Index: 885168 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.5100. Min Act: -0.0000

Data Index: 918419 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.4386. Min Act: -0.0000

Data Index: 216118 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3163. Min Act: -0.0000

Data Index: 549214 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3057. Min Act: -0.0000

Data Index: 100158 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.5340. Min Act: -0.0000

Data Index: 814699 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3498. Min Act: -0.0000

Data Index: 1344666 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3452. Min Act: -0.0000

Data Index: 558468 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3401. Min Act: -0.0000

Data Index: 1283088 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3346. Min Act: -0.0000

Data Index: 194417 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3218. Min Act: -0.0000

Data Index: 1326463 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.2047. Min Act: -0.0000

Data Index: 507324 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3238. Min Act: -0.0000

Data Index: 637125 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.2335. Min Act: -0.0000

Data Index: 260036 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.2215. Min Act: -0.0000

Data Index: 522452 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3543. Min Act: -0.0000

Data Index: 1219374 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.3143. Min Act: -0.0000

Data Index: 488893 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.4220. Min Act: -0.0000

Data Index: 380300 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 2.6116. Min Range: -2.6116

Max Act: 2.2954. Min Act: -0.0000

Data Index: 44925 (C4 (Web Text))

Max Activating Token Index: 1006