Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6129 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0647. Min Range: -1.0647

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1495959 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.9019. Min Act: -0.0000

Data Index: 793355 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1098226 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1569553 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.8133. Min Act: -0.0000

Data Index: 248121 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.8075. Min Act: 0.0000

Data Index: 94573 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1334550 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7769. Min Act: 0.0000

Data Index: 1419043 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1257910 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1342224 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.8149. Min Act: 0.0001

Data Index: 277092 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7217. Min Act: 0.0001

Data Index: 1249780 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7422. Min Act: 0.0001

Data Index: 296052 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7711. Min Act: 0.0001

Data Index: 1129134 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7139. Min Act: -0.0000

Data Index: 390235 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1258706 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1447889 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1369698 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.6842. Min Act: 0.0001

Data Index: 83155 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.0647. Min Range: -1.0647

Max Act: 0.6942. Min Act: 0.0001

Data Index: 53103 (C4 (Web Text))

Max Activating Token Index: 885