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

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

Neuron 5287 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.9913. Min Act: 0.0000

Data Index: 284579 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.9498. Min Act: 0.0000

Data Index: 734600 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8921. Min Act: 0.0000

Data Index: 448449 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1209920 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8624. Min Act: -0.0000

Data Index: 69337 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8137. Min Act: -0.0000

Data Index: 566017 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8276. Min Act: -0.0000

Data Index: 152534 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8062. Min Act: -0.0000

Data Index: 508405 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8086. Min Act: 0.0000

Data Index: 237276 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.8310. Min Act: 0.0000

Data Index: 1108498 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7542. Min Act: -0.0000

Data Index: 358021 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7914. Min Act: 0.0000

Data Index: 68971 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7394. Min Act: 0.0000

Data Index: 874110 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7426. Min Act: -0.0000

Data Index: 318111 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7170. Min Act: -0.0000

Data Index: 404651 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7394. Min Act: 0.0000

Data Index: 1116813 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1214194 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7538. Min Act: -0.0000

Data Index: 549588 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7278. Min Act: -0.0000

Data Index: 697130 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.9913. Min Range: -0.9913

Max Act: 0.7047. Min Act: -0.0000

Data Index: 871182 (C4 (Web Text))

Max Activating Token Index: 687