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

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

Neuron 3605 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.8671. Min Act: -0.0001

Data Index: 409840 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7416. Min Act: -0.0001

Data Index: 443008 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7400. Min Act: -0.0001

Data Index: 841036 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7397. Min Act: -0.0001

Data Index: 955958 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7117. Min Act: -0.0001

Data Index: 823242 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6962. Min Act: -0.0001

Data Index: 363483 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6882. Min Act: -0.0001

Data Index: 154510 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6974. Min Act: -0.0001

Data Index: 1144767 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6558. Min Act: -0.0001

Data Index: 450075 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6728. Min Act: -0.0001

Data Index: 750194 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6441. Min Act: -0.0001

Data Index: 629168 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1343628 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6632. Min Act: -0.0001

Data Index: 117490 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6267. Min Act: -0.0001

Data Index: 1201671 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6660. Min Act: -0.0001

Data Index: 331073 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6567. Min Act: -0.0001

Data Index: 913887 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6340. Min Act: -0.0001

Data Index: 880355 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6359. Min Act: -0.0001

Data Index: 131025 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6217. Min Act: -0.0001

Data Index: 489211 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6463. Min Act: -0.0001

Data Index: 664687 (C4 (Web Text))

Max Activating Token Index: 7