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

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

Neuron 3510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3521. Min Act: -0.0001

Data Index: 635070 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3292. Min Act: -0.0001

Data Index: 429081 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3011. Min Act: -0.0001

Data Index: 1039198 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3096. Min Act: -0.0001

Data Index: 1177173 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1218788 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1031309 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2614. Min Act: -0.0001

Data Index: 1169181 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1051402 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1234831 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2467. Min Act: -0.0001

Data Index: 352605 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2244. Min Act: -0.0001

Data Index: 510408 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2299. Min Act: -0.0001

Data Index: 237120 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2242. Min Act: -0.0001

Data Index: 208147 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2380. Min Act: -0.0001

Data Index: 979088 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2172. Min Act: -0.0001

Data Index: 990411 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2408. Min Act: -0.0001

Data Index: 647990 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2145. Min Act: -0.0001

Data Index: 6666 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1180122 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2044. Min Act: -0.0001

Data Index: 69985 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1961. Min Act: -0.0001

Data Index: 973764 (C4 (Web Text))

Max Activating Token Index: 108