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

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

Neuron 682 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: 0.9328. Min Range: -0.9328

Max Act: 0.9328. Min Act: -0.0000

Data Index: 147637 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1069424 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.8456. Min Act: -0.0000

Data Index: 905707 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.8485. Min Act: -0.0000

Data Index: 719234 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.8542. Min Act: -0.0000

Data Index: 50582 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.8651. Min Act: -0.0000

Data Index: 871311 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.8008. Min Act: -0.0000

Data Index: 547076 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7436. Min Act: -0.0000

Data Index: 657751 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7806. Min Act: -0.0000

Data Index: 810009 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7746. Min Act: -0.0000

Data Index: 328613 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1253838 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7194. Min Act: -0.0000

Data Index: 576978 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7358. Min Act: -0.0000

Data Index: 54449 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7472. Min Act: -0.0000

Data Index: 384280 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7010. Min Act: 0.0000

Data Index: 769096 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1274091 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1272527 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.7064. Min Act: -0.0000

Data Index: 177206 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.6565. Min Act: -0.0000

Data Index: 942742 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.9328. Min Range: -0.9328

Max Act: 0.6738. Min Act: 0.0000

Data Index: 761259 (C4 (Web Text))

Max Activating Token Index: 483