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

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

Neuron 4005 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3993. Min Act: -0.0001

Data Index: 1161621 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.1048. Min Act: -0.0001

Data Index: 869588 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.0905. Min Act: -0.0001

Data Index: 370341 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.8699. Min Act: -0.0001

Data Index: 1389716 (Python Code)

Max Activating Token Index: 861

Text #4

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.9662. Min Act: -0.0001

Data Index: 1432235 (Python Code)

Max Activating Token Index: 584

Text #5

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.9027. Min Act: -0.0001

Data Index: 1557256 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1121657 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7821. Min Act: -0.0001

Data Index: 1607087 (Python Code)

Max Activating Token Index: 849

Text #8

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7881. Min Act: -0.0001

Data Index: 682671 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7825. Min Act: -0.0001

Data Index: 1066253 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7826. Min Act: -0.0001

Data Index: 300840 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7351. Min Act: -0.0001

Data Index: 216005 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7533. Min Act: -0.0000

Data Index: 506944 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7775. Min Act: -0.0000

Data Index: 366450 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7599. Min Act: -0.0001

Data Index: 611782 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7669. Min Act: -0.0001

Data Index: 1052897 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7745. Min Act: -0.0001

Data Index: 1285553 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.6878. Min Act: -0.0001

Data Index: 669502 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.6884. Min Act: -0.0001

Data Index: 623847 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.3993. Min Range: -1.3993

Max Act: 0.7105. Min Act: -0.0001

Data Index: 1217909 (C4 (Web Text))

Max Activating Token Index: 861