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

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

Neuron 3777 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: 1.1489. Min Range: -1.1489

Max Act: 1.1489. Min Act: -0.0000

Data Index: 99403 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7672. Min Act: -0.0000

Data Index: 65027 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7961. Min Act: -0.0000

Data Index: 542914 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8373. Min Act: -0.0000

Data Index: 669276 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1555102 (Python Code)

Max Activating Token Index: 567

Text #5

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.8002. Min Act: -0.0000

Data Index: 24856 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7229. Min Act: -0.0000

Data Index: 908413 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7684. Min Act: -0.0000

Data Index: 945117 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7037. Min Act: -0.0000

Data Index: 98175 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6903. Min Act: -0.0000

Data Index: 741599 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6703. Min Act: -0.0000

Data Index: 537593 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6534. Min Act: -0.0000

Data Index: 22570 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6041. Min Act: -0.0000

Data Index: 481378 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6991. Min Act: -0.0000

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1529089 (Python Code)

Max Activating Token Index: 359

Text #15

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1491846 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6849. Min Act: -0.0000

Data Index: 919983 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1248460 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.7027. Min Act: -0.0000

Data Index: 31842 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 1.1489. Min Range: -1.1489

Max Act: 0.6047. Min Act: -0.0000

Data Index: 818326 (C4 (Web Text))

Max Activating Token Index: 233