Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3500 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.6194. Min Act: -0.0000

Data Index: 679355 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5968. Min Act: -0.0000

Data Index: 72144 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.6475. Min Act: -0.0000

Data Index: 338740 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5499. Min Act: -0.0001

Data Index: 423481 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.6186. Min Act: -0.0001

Data Index: 759246 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5047. Min Act: -0.0000

Data Index: 148342 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5759. Min Act: -0.0001

Data Index: 647723 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5431. Min Act: -0.0000

Data Index: 519398 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5618. Min Act: -0.0000

Data Index: 648050 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5422. Min Act: -0.0001

Data Index: 919406 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5371. Min Act: -0.0000

Data Index: 34280 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5307. Min Act: -0.0001

Data Index: 177168 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5388. Min Act: -0.0001

Data Index: 1325482 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4848. Min Act: -0.0000

Data Index: 134789 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1059378 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4724. Min Act: -0.0001

Data Index: 951464 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.5261. Min Act: -0.0001

Data Index: 151063 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4481. Min Act: -0.0000

Data Index: 142549 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4616. Min Act: -0.0000

Data Index: 469503 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.6475. Min Range: -0.6475

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1178988 (C4 (Web Text))

Max Activating Token Index: 994