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

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

Neuron 4661 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: 2.3970. Min Range: -2.3970

Max Act: 2.3442. Min Act: -0.0000

Data Index: 576804 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 2.3970. Min Range: -2.3970

Max Act: 2.3970. Min Act: -0.0000

Data Index: 866020 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 2.3970. Min Range: -2.3970

Max Act: 2.2963. Min Act: -0.0000

Data Index: 1342212 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 2.3970. Min Range: -2.3970

Max Act: 2.1475. Min Act: -0.0000

Data Index: 102932 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 2.3970. Min Range: -2.3970

Max Act: 2.0228. Min Act: -0.0000

Data Index: 960154 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.3970. Min Range: -2.3970

Max Act: 2.0521. Min Act: -0.0000

Data Index: 98406 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 2.3970. Min Range: -2.3970

Max Act: 2.0195. Min Act: -0.0000

Data Index: 1135296 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.8128. Min Act: -0.0000

Data Index: 99667 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.8825. Min Act: -0.0000

Data Index: 899064 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.8192. Min Act: -0.0000

Data Index: 373962 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.8896. Min Act: -0.0000

Data Index: 917747 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.7795. Min Act: -0.0000

Data Index: 1175047 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.7545. Min Act: -0.0000

Data Index: 512193 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.8117. Min Act: -0.0000

Data Index: 97080 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1313223 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.8091. Min Act: -0.0000

Data Index: 837442 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.7050. Min Act: -0.0000

Data Index: 1289391 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.7945. Min Act: -0.0000

Data Index: 635202 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.7884. Min Act: -0.0000

Data Index: 43332 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 2.3970. Min Range: -2.3970

Max Act: 1.7796. Min Act: -0.0000

Data Index: 214437 (C4 (Web Text))

Max Activating Token Index: 26