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

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

Neuron 3637 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1332. Min Act: -0.0001

Data Index: 863154 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1048. Min Act: -0.0001

Data Index: 533456 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1025. Min Act: -0.0001

Data Index: 615788 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1288. Min Act: -0.0001

Data Index: 395397 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0935. Min Act: -0.0001

Data Index: 931184 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0871. Min Act: -0.0001

Data Index: 553592 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1305262 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0665. Min Act: -0.0001

Data Index: 288148 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1264602 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0586. Min Act: -0.0001

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0561. Min Act: -0.0001

Data Index: 399168 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0659. Min Act: -0.0001

Data Index: 645076 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1161994 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1119562 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0576. Min Act: -0.0001

Data Index: 151718 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0562. Min Act: -0.0001

Data Index: 235437 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0512. Min Act: -0.0001

Data Index: 506333 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1082881 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1078339 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0516. Min Act: -0.0001

Data Index: 291132 (C4 (Web Text))

Max Activating Token Index: 246