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

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

Neuron 2108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.6168. Min Act: -0.0000

Data Index: 101316 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.2809. Min Act: -0.0000

Data Index: 514561 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.2131. Min Act: -0.0000

Data Index: 457286 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1033262 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1316301 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1005. Min Act: -0.0000

Data Index: 429403 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0684. Min Act: -0.0000

Data Index: 30586 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0693. Min Act: -0.0000

Data Index: 358777 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1040. Min Act: -0.0000

Data Index: 582319 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0465. Min Act: -0.0000

Data Index: 984128 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1230290 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0137. Min Act: -0.0000

Data Index: 627630 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.1051. Min Act: -0.0000

Data Index: 312313 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1215693 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1293551 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9163. Min Act: -0.0000

Data Index: 140672 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1007415 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0051. Min Act: -0.0000

Data Index: 339457 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.6168. Min Range: -1.6168

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1000275 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.6168. Min Range: -1.6168

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1231758 (C4 (Web Text))

Max Activating Token Index: 935