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

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

Neuron 3786 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: 2.7250. Min Range: -2.7250

Max Act: 2.7250. Min Act: -0.0000

Data Index: 916317 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.2538. Min Act: -0.0000

Data Index: 1314089 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.2748. Min Act: -0.0000

Data Index: 528287 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0588. Min Act: -0.0000

Data Index: 512723 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0556. Min Act: -0.0000

Data Index: 1115917 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.2050. Min Act: -0.0000

Data Index: 56330 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0948. Min Act: -0.0000

Data Index: 950349 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.9303. Min Act: -0.0000

Data Index: 774666 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0044. Min Act: -0.0000

Data Index: 1073927 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0076. Min Act: -0.0000

Data Index: 979180 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.8903. Min Act: -0.0000

Data Index: 70686 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.1161. Min Act: -0.0000

Data Index: 1026198 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.9451. Min Act: -0.0000

Data Index: 1239804 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.1544. Min Act: -0.0000

Data Index: 1171845 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.8412. Min Act: -0.0000

Data Index: 143243 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.8332. Min Act: -0.0000

Data Index: 794686 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.9011. Min Act: -0.0000

Data Index: 145382 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0738. Min Act: -0.0000

Data Index: 897676 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.9179. Min Act: -0.0000

Data Index: 783053 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.9048. Min Act: -0.0000

Data Index: 1261170 (C4 (Web Text))

Max Activating Token Index: 577