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

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

Neuron 1136 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: 0.2693. Min Range: -0.2693

Max Act: 0.2597. Min Act: -0.0001

Data Index: 926100 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2547. Min Act: -0.0001

Data Index: 396293 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2486. Min Act: -0.0001

Data Index: 120079 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2647. Min Act: -0.0001

Data Index: 160133 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2545. Min Act: -0.0001

Data Index: 974478 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2693. Min Act: -0.0001

Data Index: 753230 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2212. Min Act: -0.0001

Data Index: 1249670 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1021303 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2348. Min Act: -0.0000

Data Index: 91216 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2152. Min Act: -0.0001

Data Index: 194283 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2178. Min Act: -0.0001

Data Index: 248619 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2130. Min Act: -0.0000

Data Index: 873216 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1296448 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2103. Min Act: -0.0000

Data Index: 770806 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2025. Min Act: -0.0001

Data Index: 1352671 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1024319 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2009. Min Act: -0.0000

Data Index: 88067 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1984. Min Act: -0.0000

Data Index: 911077 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1303980 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.1962. Min Act: -0.0001

Data Index: 469143 (C4 (Web Text))

Max Activating Token Index: 892