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

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

Neuron 534 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4990. Min Act: -0.0000

Data Index: 187639 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4340. Min Act: -0.0000

Data Index: 661198 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1082750 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3928. Min Act: -0.0000

Data Index: 581993 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1025140 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1088325 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1243983 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1184868 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3757. Min Act: -0.0000

Data Index: 409901 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3687. Min Act: -0.0000

Data Index: 982594 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3649. Min Act: -0.0000

Data Index: 457434 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3284. Min Act: -0.0000

Data Index: 247707 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1108352 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3176. Min Act: -0.0000

Data Index: 961255 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3160. Min Act: -0.0000

Data Index: 34527 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.2803. Min Act: -0.0000

Data Index: 859453 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1134739 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3096. Min Act: 0.0000

Data Index: 624109 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3126. Min Act: -0.0000

Data Index: 562350 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.4990. Min Range: -0.4990

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1258989 (C4 (Web Text))

Max Activating Token Index: 164