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

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

Neuron 2875 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.8536. Min Act: -0.0000

Data Index: 852754 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.7561. Min Act: -0.0000

Data Index: 137483 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.7326. Min Act: -0.0000

Data Index: 956526 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5579. Min Act: -0.0000

Data Index: 310917 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.4609. Min Act: -0.0000

Data Index: 763392 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5407. Min Act: -0.0000

Data Index: 328721 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1260027 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1116629 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.4347. Min Act: -0.0000

Data Index: 711124 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1022433 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1234128 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5437. Min Act: -0.0000

Data Index: 684253 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1348822 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1047634 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5149. Min Act: -0.0000

Data Index: 102071 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5215. Min Act: -0.0000

Data Index: 126752 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1194357 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1119648 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5229. Min Act: -0.0000

Data Index: 772273 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.8536. Min Range: -0.8536

Max Act: 0.5066. Min Act: -0.0000

Data Index: 152334 (C4 (Web Text))

Max Activating Token Index: 457