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

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

Neuron 4446 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: 0.3939. Min Range: -0.3939

Max Act: 0.3939. Min Act: -0.0000

Data Index: 117130 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3933. Min Act: -0.0000

Data Index: 715974 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3678. Min Act: -0.0000

Data Index: 376922 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3468. Min Act: -0.0000

Data Index: 895524 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3621. Min Act: -0.0000

Data Index: 968391 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3414. Min Act: -0.0000

Data Index: 298118 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1272303 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1193230 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3512. Min Act: -0.0000

Data Index: 291121 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3459. Min Act: -0.0000

Data Index: 79205 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1241500 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3256. Min Act: -0.0000

Data Index: 816253 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3346. Min Act: -0.0000

Data Index: 460099 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3472. Min Act: -0.0000

Data Index: 14979 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3319. Min Act: -0.0000

Data Index: 769691 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3194. Min Act: -0.0000

Data Index: 640474 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3325. Min Act: -0.0000

Data Index: 305633 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3235. Min Act: -0.0000

Data Index: 389890 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3176. Min Act: -0.0000

Data Index: 464299 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3271. Min Act: -0.0000

Data Index: 627885 (C4 (Web Text))

Max Activating Token Index: 465