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

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

Neuron 5480 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1086350 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.0707. Min Range: -1.0707

Max Act: 1.0707. Min Act: -0.0000

Data Index: 488499 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8264. Min Act: -0.0000

Data Index: 595230 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8029. Min Act: -0.0000

Data Index: 543815 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8033. Min Act: -0.0000

Data Index: 192024 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8049. Min Act: -0.0000

Data Index: 185524 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1071293 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.8281. Min Act: -0.0000

Data Index: 200657 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7548. Min Act: -0.0000

Data Index: 924094 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.6979. Min Act: -0.0000

Data Index: 359464 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.6885. Min Act: -0.0000

Data Index: 344988 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7319. Min Act: -0.0000

Data Index: 60498 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.6751. Min Act: -0.0000

Data Index: 401296 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.6708. Min Act: -0.0000

Data Index: 589512 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7040. Min Act: -0.0000

Data Index: 18990 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.6987. Min Act: -0.0000

Data Index: 95052 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.6932. Min Act: -0.0000

Data Index: 783233 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1267702 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7359. Min Act: -0.0000

Data Index: 638449 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.0707. Min Range: -1.0707

Max Act: 0.7363. Min Act: -0.0000

Data Index: 275688 (C4 (Web Text))

Max Activating Token Index: 179