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

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

Neuron 4276 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: 0.1424. Min Range: -0.1424

Max Act: 0.1410. Min Act: -0.0000

Data Index: 191221 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1424. Min Act: -0.0000

Data Index: 578651 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1311. Min Act: -0.0000

Data Index: 655654 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1288. Min Act: -0.0000

Data Index: 323020 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1152022 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1162. Min Act: -0.0000

Data Index: 53174 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1190. Min Act: -0.0000

Data Index: 45151 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1204629 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1177. Min Act: -0.0000

Data Index: 716599 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1180. Min Act: -0.0000

Data Index: 984748 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1310622 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1061192 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1089. Min Act: -0.0000

Data Index: 605320 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1073. Min Act: -0.0000

Data Index: 812206 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1212099 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1139632 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1009. Min Act: -0.0000

Data Index: 563928 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.1035. Min Act: -0.0000

Data Index: 920479 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.1424. Min Range: -0.1424

Max Act: 0.0989. Min Act: -0.0000

Data Index: 597122 (C4 (Web Text))

Max Activating Token Index: 427