Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2750 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.3066. Min Act: -0.0001

Data Index: 274484 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2662. Min Act: -0.0001

Data Index: 867562 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2296. Min Act: -0.0001

Data Index: 1248404 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2308. Min Act: -0.0000

Data Index: 65713 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2338. Min Act: -0.0001

Data Index: 198301 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2228. Min Act: -0.0001

Data Index: 1371346 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1600556 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1107817 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1147422 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2136. Min Act: -0.0000

Data Index: 317140 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2113. Min Act: -0.0001

Data Index: 270675 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1607401 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2124. Min Act: -0.0001

Data Index: 856211 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2097. Min Act: -0.0000

Data Index: 430449 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2090. Min Act: -0.0001

Data Index: 970949 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2115. Min Act: -0.0000

Data Index: 202493 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2051. Min Act: -0.0001

Data Index: 650165 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2029. Min Act: -0.0000

Data Index: 227927 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.1975. Min Act: -0.0000

Data Index: 496960 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2027. Min Act: -0.0000

Data Index: 463898 (C4 (Web Text))

Max Activating Token Index: 816