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

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

Neuron 1610 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: 2.8406. Min Range: -2.8406

Max Act: 2.8406. Min Act: -0.0000

Data Index: 1379807 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 2.8406. Min Range: -2.8406

Max Act: 2.7895. Min Act: -0.0000

Data Index: 757539 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 2.8406. Min Range: -2.8406

Max Act: 2.7383. Min Act: -0.0000

Data Index: 1360022 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 2.8406. Min Range: -2.8406

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1523132 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 2.8406. Min Range: -2.8406

Max Act: 2.1882. Min Act: -0.0000

Data Index: 1405177 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.9067. Min Act: -0.0000

Data Index: 182962 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.7318. Min Act: -0.0000

Data Index: 1327337 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.7016. Min Act: -0.0000

Data Index: 537767 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.6946. Min Act: -0.0000

Data Index: 882998 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.6043. Min Act: -0.0000

Data Index: 115810 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.6369. Min Act: -0.0000

Data Index: 8148 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.5732. Min Act: -0.0000

Data Index: 932582 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1158106 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.5574. Min Act: -0.0000

Data Index: 820110 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1195012 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.5633. Min Act: -0.0000

Data Index: 858455 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.4863. Min Act: -0.0000

Data Index: 573818 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.3706. Min Act: -0.0000

Data Index: 77179 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.3763. Min Act: -0.0000

Data Index: 6727 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 2.8406. Min Range: -2.8406

Max Act: 1.4490. Min Act: 0.0000

Data Index: 188545 (C4 (Web Text))

Max Activating Token Index: 486