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

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

Neuron 3210 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.4068. Min Act: -0.0001

Data Index: 1583803 (Python Code)

Max Activating Token Index: 499

Text #1

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1475067 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3370. Min Act: -0.0001

Data Index: 732790 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3197. Min Act: -0.0001

Data Index: 642544 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3757. Min Act: -0.0001

Data Index: 122558 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3383. Min Act: -0.0001

Data Index: 1275473 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3271. Min Act: -0.0001

Data Index: 563865 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3126. Min Act: -0.0001

Data Index: 1637157 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3391. Min Act: -0.0001

Data Index: 737439 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3445. Min Act: -0.0001

Data Index: 1187832 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3080. Min Act: -0.0001

Data Index: 251064 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3010. Min Act: -0.0001

Data Index: 723474 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3234. Min Act: -0.0001

Data Index: 1501558 (Python Code)

Max Activating Token Index: 282

Text #13

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3013. Min Act: -0.0001

Data Index: 278377 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1008789 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1167493 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.2913. Min Act: -0.0001

Data Index: 1172690 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.2719. Min Act: -0.0001

Data Index: 1327528 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.3029. Min Act: -0.0001

Data Index: 17670 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.4426. Min Range: -0.4426

Max Act: 0.2712. Min Act: -0.0001

Data Index: 93052 (C4 (Web Text))

Max Activating Token Index: 94