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

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

Neuron 3140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8043. Min Act: -0.0000

Data Index: 210778 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8657. Min Act: -0.0000

Data Index: 15315 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1302751 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.8210. Min Act: -0.0000

Data Index: 356866 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7506. Min Act: -0.0000

Data Index: 190414 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.7024. Min Act: -0.0000

Data Index: 472449 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6967. Min Act: -0.0000

Data Index: 854276 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6004. Min Act: -0.0000

Data Index: 723595 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6319. Min Act: -0.0000

Data Index: 509823 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6269. Min Act: -0.0000

Data Index: 591666 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.5990. Min Act: -0.0000

Data Index: 633043 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.5975. Min Act: -0.0000

Data Index: 674956 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6065. Min Act: -0.0000

Data Index: 440913 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6299. Min Act: -0.0000

Data Index: 541902 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1180647 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1301697 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.6415. Min Act: -0.0000

Data Index: 222958 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.5782. Min Act: -0.0000

Data Index: 221035 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.5266. Min Act: -0.0000

Data Index: 796579 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.8657. Min Range: -0.8657

Max Act: 0.5628. Min Act: -0.0000

Data Index: 946681 (C4 (Web Text))

Max Activating Token Index: 752