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

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

Neuron 2449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0364. Min Range: -1.0364

Max Act: 1.0364. Min Act: -0.0001

Data Index: 1106060 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8894. Min Act: -0.0001

Data Index: 812710 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8821. Min Act: -0.0001

Data Index: 761013 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8784. Min Act: -0.0001

Data Index: 827641 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8461. Min Act: -0.0001

Data Index: 1015594 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8633. Min Act: -0.0001

Data Index: 923118 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8593. Min Act: -0.0001

Data Index: 760871 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8557. Min Act: -0.0000

Data Index: 950122 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8149. Min Act: -0.0001

Data Index: 643126 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8271. Min Act: -0.0001

Data Index: 552869 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7925. Min Act: -0.0001

Data Index: 304277 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7847. Min Act: -0.0001

Data Index: 846775 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8046. Min Act: -0.0001

Data Index: 547469 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7210. Min Act: -0.0000

Data Index: 150386 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7845. Min Act: -0.0001

Data Index: 116466 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7605. Min Act: -0.0001

Data Index: 360765 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7819. Min Act: -0.0001

Data Index: 706725 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7832. Min Act: -0.0001

Data Index: 108364 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1347883 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7777. Min Act: -0.0001

Data Index: 1176821 (C4 (Web Text))

Max Activating Token Index: 350