Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1457 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.9497. Min Act: -0.0001

Data Index: 136932 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8557. Min Act: -0.0001

Data Index: 1258842 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8467. Min Act: -0.0001

Data Index: 740431 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6277. Min Act: -0.0000

Data Index: 168940 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6798. Min Act: -0.0000

Data Index: 264194 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6706. Min Act: -0.0001

Data Index: 680194 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.7322. Min Act: -0.0000

Data Index: 880343 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6649. Min Act: -0.0001

Data Index: 1330611 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.7542. Min Act: -0.0001

Data Index: 186265 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1032500 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.7819. Min Act: -0.0000

Data Index: 1105717 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6255. Min Act: -0.0001

Data Index: 1280706 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.5656. Min Act: -0.0001

Data Index: 963316 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6412. Min Act: -0.0001

Data Index: 938009 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6563. Min Act: -0.0001

Data Index: 48012 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1071759 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.5772. Min Act: -0.0001

Data Index: 591179 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.4767. Min Act: -0.0001

Data Index: 572703 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6424. Min Act: -0.0000

Data Index: 495506 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.5017. Min Act: -0.0001

Data Index: 828570 (C4 (Web Text))

Max Activating Token Index: 34