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

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

Neuron 3670 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: 1.6520. Min Range: -1.6520

Max Act: 1.6096. Min Act: -0.0001

Data Index: 752859 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.6520. Min Act: -0.0001

Data Index: 99045 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.5618. Min Act: -0.0001

Data Index: 1269778 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.4333. Min Act: -0.0001

Data Index: 793780 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.4981. Min Act: -0.0001

Data Index: 1112639 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.4428. Min Act: -0.0001

Data Index: 718100 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.3707. Min Act: -0.0001

Data Index: 386953 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.4457. Min Act: -0.0001

Data Index: 748366 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.3491. Min Act: -0.0001

Data Index: 526181 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.3543. Min Act: -0.0001

Data Index: 190068 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2217. Min Act: -0.0001

Data Index: 1052189 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.3146. Min Act: -0.0001

Data Index: 1255357 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2691. Min Act: -0.0001

Data Index: 771635 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2199. Min Act: -0.0001

Data Index: 1226960 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2133. Min Act: -0.0001

Data Index: 347548 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2172. Min Act: -0.0001

Data Index: 1002377 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1972. Min Act: -0.0001

Data Index: 486913 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1277. Min Act: -0.0001

Data Index: 936105 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2274. Min Act: -0.0001

Data Index: 626479 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1825. Min Act: -0.0001

Data Index: 877504 (C4 (Web Text))

Max Activating Token Index: 26