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

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

Neuron 1655 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4880. Min Act: -0.0001

Data Index: 1292345 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3740. Min Act: -0.0001

Data Index: 506168 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3447. Min Act: -0.0000

Data Index: 658966 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3470. Min Act: -0.0000

Data Index: 986573 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3296. Min Act: -0.0000

Data Index: 593816 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3254. Min Act: -0.0000

Data Index: 130039 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3136. Min Act: -0.0000

Data Index: 226469 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3176. Min Act: -0.0001

Data Index: 597802 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3033. Min Act: -0.0000

Data Index: 646962 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3020. Min Act: -0.0000

Data Index: 967693 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2985. Min Act: -0.0001

Data Index: 821227 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1103647 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3125. Min Act: -0.0000

Data Index: 330276 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2813. Min Act: -0.0000

Data Index: 987257 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1061100 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2892. Min Act: -0.0001

Data Index: 696086 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2610. Min Act: -0.0001

Data Index: 227432 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2688. Min Act: -0.0000

Data Index: 811363 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2751. Min Act: -0.0000

Data Index: 730433 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2502. Min Act: -0.0000

Data Index: 569953 (C4 (Web Text))

Max Activating Token Index: 330