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

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

Neuron 3443 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: 0.1572. Min Range: -0.1572

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1296791 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1320238 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1465. Min Act: -0.0001

Data Index: 995440 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1333. Min Act: -0.0001

Data Index: 63643 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1263. Min Act: -0.0001

Data Index: 732884 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1319. Min Act: -0.0001

Data Index: 352417 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1244758 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1203. Min Act: -0.0000

Data Index: 307531 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1145. Min Act: -0.0000

Data Index: 640552 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1186. Min Act: -0.0001

Data Index: 333577 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1274175 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1086034 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1134. Min Act: -0.0000

Data Index: 291099 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1144. Min Act: -0.0001

Data Index: 705197 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1123. Min Act: -0.0000

Data Index: 524662 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1002257 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1112. Min Act: -0.0000

Data Index: 609417 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1120. Min Act: -0.0000

Data Index: 217654 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1124172 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.1572. Min Range: -0.1572

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1241026 (C4 (Web Text))

Max Activating Token Index: 189