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

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

Neuron 1708 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2798. Min Act: -0.0001

Data Index: 782476 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.3402. Min Act: -0.0001

Data Index: 962548 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.2342. Min Act: -0.0001

Data Index: 76262 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.1692. Min Act: -0.0001

Data Index: 151611 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.0400. Min Act: -0.0001

Data Index: 329400 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.0402. Min Act: -0.0001

Data Index: 1002274 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.0981. Min Act: -0.0001

Data Index: 864728 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.0452. Min Act: -0.0001

Data Index: 266264 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.3402. Min Range: -1.3402

Max Act: 1.0339. Min Act: -0.0001

Data Index: 527765 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9911. Min Act: -0.0001

Data Index: 71629 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9326. Min Act: -0.0001

Data Index: 688488 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9385. Min Act: -0.0001

Data Index: 715057 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9537. Min Act: -0.0001

Data Index: 928602 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9343. Min Act: -0.0001

Data Index: 1026182 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9257. Min Act: -0.0001

Data Index: 686709 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9321. Min Act: -0.0001

Data Index: 305878 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.8887. Min Act: -0.0001

Data Index: 891990 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.8697. Min Act: -0.0001

Data Index: 621736 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.9178. Min Act: -0.0001

Data Index: 356246 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.3402. Min Range: -1.3402

Max Act: 0.8592. Min Act: -0.0001

Data Index: 1131195 (C4 (Web Text))

Max Activating Token Index: 490