Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2668 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.9659. Min Act: -0.0001

Data Index: 302892 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.8977. Min Act: -0.0001

Data Index: 102200 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.8041. Min Act: -0.0001

Data Index: 176470 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.7636. Min Act: -0.0001

Data Index: 407300 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.7494. Min Act: -0.0000

Data Index: 758864 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6479. Min Act: -0.0001

Data Index: 946720 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6973. Min Act: -0.0001

Data Index: 326918 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.7095. Min Act: -0.0001

Data Index: 1325816 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6552. Min Act: -0.0001

Data Index: 160198 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6682. Min Act: -0.0001

Data Index: 1122949 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6448. Min Act: -0.0000

Data Index: 919029 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6069. Min Act: -0.0000

Data Index: 558165 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5572. Min Act: -0.0001

Data Index: 1065245 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.4972. Min Act: -0.0001

Data Index: 341528 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5933. Min Act: -0.0000

Data Index: 656590 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5483. Min Act: -0.0001

Data Index: 406712 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5799. Min Act: -0.0001

Data Index: 328702 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5210. Min Act: -0.0001

Data Index: 629517 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5612. Min Act: -0.0001

Data Index: 1415648 (Python Code)

Max Activating Token Index: 937

Text #19

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5902. Min Act: -0.0001

Data Index: 772399 (C4 (Web Text))

Max Activating Token Index: 902