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

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

Neuron 1114 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1934. Min Range: -1.1934

Max Act: 1.1934. Min Act: -0.0000

Data Index: 950719 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.1934. Min Range: -1.1934

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1211427 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 1.1934. Min Range: -1.1934

Max Act: 1.0196. Min Act: -0.0000

Data Index: 892209 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 1.1934. Min Range: -1.1934

Max Act: 1.1241. Min Act: -0.0000

Data Index: 472310 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 1.1934. Min Range: -1.1934

Max Act: 1.0606. Min Act: -0.0000

Data Index: 782352 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.1934. Min Range: -1.1934

Max Act: 1.0264. Min Act: -0.0000

Data Index: 87392 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1245530 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.1934. Min Range: -1.1934

Max Act: 1.0249. Min Act: -0.0000

Data Index: 103631 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.9131. Min Act: -0.0000

Data Index: 716226 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.9065. Min Act: -0.0000

Data Index: 419290 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.9466. Min Act: -0.0000

Data Index: 140723 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.9356. Min Act: -0.0000

Data Index: 4326 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.8879. Min Act: -0.0000

Data Index: 648139 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.8803. Min Act: -0.0000

Data Index: 748904 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.8656. Min Act: -0.0000

Data Index: 882274 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.8517. Min Act: -0.0000

Data Index: 512919 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1173480 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1233217 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1041702 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.1934. Min Range: -1.1934

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1076399 (C4 (Web Text))

Max Activating Token Index: 770