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

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

Neuron 3395 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: 1.2222. Min Range: -1.2222

Max Act: 1.2222. Min Act: -0.0001

Data Index: 107487 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.9942. Min Act: -0.0001

Data Index: 753176 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.8105. Min Act: -0.0001

Data Index: 396203 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.8433. Min Act: -0.0001

Data Index: 1173026 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.8605. Min Act: -0.0001

Data Index: 951364 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.8040. Min Act: -0.0001

Data Index: 919418 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7325. Min Act: -0.0001

Data Index: 1237623 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7630. Min Act: -0.0001

Data Index: 417386 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7828. Min Act: -0.0001

Data Index: 70968 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1286452 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7506. Min Act: -0.0001

Data Index: 1277596 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7967. Min Act: -0.0001

Data Index: 386783 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7644. Min Act: -0.0001

Data Index: 577040 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.6785. Min Act: -0.0001

Data Index: 642974 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1263899 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7083. Min Act: -0.0001

Data Index: 142120 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7249. Min Act: -0.0001

Data Index: 472496 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7066. Min Act: -0.0001

Data Index: 304015 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7227. Min Act: -0.0001

Data Index: 3374 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.2222. Min Range: -1.2222

Max Act: 0.7035. Min Act: -0.0001

Data Index: 1359490 (C4 (Web Text))

Max Activating Token Index: 309