Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2563 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.1114. Min Act: -0.0003

Data Index: 1117906 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0513. Min Act: -0.0003

Data Index: 668040 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8538. Min Act: -0.0003

Data Index: 756290 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0684. Min Act: -0.0003

Data Index: 1089749 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0195. Min Act: -0.0003

Data Index: 47755 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9888. Min Act: -0.0003

Data Index: 509787 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0447. Min Act: -0.0003

Data Index: 789366 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.1394. Min Act: -0.0003

Data Index: 1035726 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9422. Min Act: -0.0003

Data Index: 390530 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9498. Min Act: -0.0003

Data Index: 264929 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9832. Min Act: -0.0003

Data Index: 536218 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0080. Min Act: -0.0003

Data Index: 1097647 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9136. Min Act: -0.0003

Data Index: 148476 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9500. Min Act: -0.0003

Data Index: 19070 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8684. Min Act: -0.0003

Data Index: 722564 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9333. Min Act: -0.0003

Data Index: 500134 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.0319. Min Act: -0.0003

Data Index: 196609 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8701. Min Act: -0.0003

Data Index: 1242409 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9272. Min Act: -0.0003

Data Index: 163830 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9241. Min Act: -0.0003

Data Index: 1341081 (C4 (Web Text))

Max Activating Token Index: 284