Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1614 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0324. Min Range: -4.0324

Max Act: 4.0324. Min Act: -0.0001

Data Index: 943524 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.9834. Min Act: -0.0001

Data Index: 557190 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.8469. Min Act: -0.0001

Data Index: 1155688 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.7408. Min Act: -0.0001

Data Index: 939102 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.7911. Min Act: -0.0000

Data Index: 161791 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.7606. Min Act: -0.0001

Data Index: 662288 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4362. Min Act: -0.0001

Data Index: 467120 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.3327. Min Act: -0.0001

Data Index: 30872 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.0265. Min Act: -0.0001

Data Index: 502988 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.2864. Min Act: -0.0000

Data Index: 438274 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.5510. Min Act: -0.0001

Data Index: 1205825 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4491. Min Act: -0.0000

Data Index: 816930 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.1469. Min Act: -0.0001

Data Index: 1155682 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 4.0324. Min Range: -4.0324

Max Act: 2.9935. Min Act: -0.0001

Data Index: 1220004 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.1173. Min Act: -0.0001

Data Index: 379975 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.2378. Min Act: -0.0001

Data Index: 843666 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.1082. Min Act: -0.0001

Data Index: 1243337 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 4.0324. Min Range: -4.0324

Max Act: 2.9295. Min Act: -0.0001

Data Index: 1073475 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4998. Min Act: -0.0001

Data Index: 1085153 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.1510. Min Act: -0.0001

Data Index: 1287572 (C4 (Web Text))

Max Activating Token Index: 502