Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1982 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.8056. Min Act: -0.0000

Data Index: 1330985 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.5462. Min Act: -0.0000

Data Index: 137223 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.5258. Min Act: -0.0000

Data Index: 37198 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.4830. Min Act: -0.0000

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.4790. Min Act: -0.0000

Data Index: 132628 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.4435. Min Act: -0.0000

Data Index: 551587 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.4101. Min Act: -0.0000

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1006484 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1021893 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3022. Min Act: -0.0000

Data Index: 370 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1170521 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1065328 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.2658. Min Act: -0.0000

Data Index: 395508 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.4210. Min Act: -0.0000

Data Index: 882983 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3334. Min Act: -0.0000

Data Index: 696827 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.2944. Min Act: -0.0000

Data Index: 66681 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3122. Min Act: -0.0000

Data Index: 101364 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3304. Min Act: -0.0000

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3656. Min Act: -0.0000

Data Index: 132456 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 1.8056. Min Range: -1.8056

Max Act: 1.3280. Min Act: -0.0000

Data Index: 374551 (C4 (Web Text))

Max Activating Token Index: 293