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

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

Neuron 225 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: 1.0177. Min Range: -1.0177

Max Act: 0.9590. Min Act: -0.0001

Data Index: 633553 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 1.0177. Min Range: -1.0177

Max Act: 1.0020. Min Act: -0.0001

Data Index: 1119804 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9413. Min Act: -0.0001

Data Index: 338805 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9579. Min Act: -0.0001

Data Index: 536935 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9526. Min Act: -0.0001

Data Index: 105275 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9204. Min Act: -0.0001

Data Index: 494895 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9229. Min Act: -0.0001

Data Index: 750004 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9268. Min Act: -0.0001

Data Index: 944826 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9480. Min Act: -0.0001

Data Index: 1084154 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1176882 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9409. Min Act: -0.0001

Data Index: 878530 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8836. Min Act: -0.0001

Data Index: 83863 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9714. Min Act: -0.0001

Data Index: 1280925 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9016. Min Act: -0.0001

Data Index: 997220 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8473. Min Act: -0.0001

Data Index: 1069391 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8967. Min Act: -0.0001

Data Index: 742913 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.0177. Min Range: -1.0177

Max Act: 1.0177. Min Act: -0.0001

Data Index: 390036 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8625. Min Act: -0.0001

Data Index: 1303581 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7877. Min Act: -0.0001

Data Index: 1334820 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9410. Min Act: -0.0001

Data Index: 790821 (C4 (Web Text))

Max Activating Token Index: 435