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

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

Neuron 3262 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.2890. Min Act: -0.0000

Data Index: 195575 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1657046 (Python Code)

Max Activating Token Index: 694

Text #2

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.9529. Min Act: -0.0000

Data Index: 584439 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0459. Min Act: -0.0000

Data Index: 110214 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.8772. Min Act: -0.0000

Data Index: 730823 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.9054. Min Act: -0.0000

Data Index: 819593 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.7538. Min Act: -0.0000

Data Index: 567401 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.6995. Min Act: -0.0000

Data Index: 722628 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5976. Min Act: 0.0001

Data Index: 939855 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5946. Min Act: -0.0000

Data Index: 576913 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1237596 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.6200. Min Act: 0.0000

Data Index: 166879 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.6154. Min Act: 0.0000

Data Index: 369407 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5053. Min Act: -0.0000

Data Index: 612033 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5195. Min Act: -0.0000

Data Index: 276081 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1019901 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1393069 (Python Code)

Max Activating Token Index: 530

Text #17

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5467. Min Act: -0.0000

Data Index: 954162 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5118. Min Act: -0.0000

Data Index: 177884 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.2890. Min Range: -1.2890

Max Act: 0.5582. Min Act: -0.0000

Data Index: 439776 (C4 (Web Text))

Max Activating Token Index: 16