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

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

Neuron 3600 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6965. Min Act: -0.0001

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6949. Min Act: -0.0001

Data Index: 132448 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6654. Min Act: -0.0001

Data Index: 1087527 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6510. Min Act: -0.0001

Data Index: 870930 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6430. Min Act: -0.0001

Data Index: 395085 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6355. Min Act: -0.0001

Data Index: 464391 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5639. Min Act: -0.0001

Data Index: 142205 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5607. Min Act: -0.0001

Data Index: 687234 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.6004. Min Act: -0.0001

Data Index: 425602 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5971. Min Act: -0.0001

Data Index: 1034072 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5893. Min Act: -0.0001

Data Index: 205220 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5886. Min Act: -0.0001

Data Index: 155692 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5705. Min Act: -0.0001

Data Index: 1179892 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5950. Min Act: -0.0001

Data Index: 194750 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5564. Min Act: -0.0001

Data Index: 851913 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5545. Min Act: -0.0001

Data Index: 832120 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5691. Min Act: -0.0001

Data Index: 501271 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5870. Min Act: -0.0001

Data Index: 1335434 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5758. Min Act: -0.0001

Data Index: 1253420 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.6965. Min Range: -0.6965

Max Act: 0.5657. Min Act: -0.0001

Data Index: 632470 (C4 (Web Text))

Max Activating Token Index: 353