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

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

Neuron 1995 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1616. Min Act: -0.0000

Data Index: 726809 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1362. Min Act: -0.0000

Data Index: 552965 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1351. Min Act: -0.0000

Data Index: 811977 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1179815 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1282. Min Act: -0.0001

Data Index: 392702 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1301. Min Act: -0.0001

Data Index: 455789 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1285. Min Act: -0.0001

Data Index: 251119 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1248. Min Act: -0.0000

Data Index: 299839 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1166330 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1129. Min Act: -0.0000

Data Index: 947546 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1230. Min Act: -0.0000

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1140. Min Act: -0.0000

Data Index: 50389 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1176. Min Act: -0.0001

Data Index: 190546 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1145. Min Act: -0.0000

Data Index: 950464 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1103. Min Act: -0.0000

Data Index: 446836 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1254561 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1594218 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1103904 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1072. Min Act: -0.0000

Data Index: 97974 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1228. Min Act: -0.0001

Data Index: 911462 (C4 (Web Text))

Max Activating Token Index: 648