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

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

Neuron 6042 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4911. Min Range: -6.4911

Max Act: 6.4911. Min Act: -0.0000

Data Index: 1251125 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 6.4911. Min Range: -6.4911

Max Act: 5.9036. Min Act: -0.0000

Data Index: 382620 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 6.4911. Min Range: -6.4911

Max Act: 5.5434. Min Act: -0.0000

Data Index: 1087544 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 6.4911. Min Range: -6.4911

Max Act: 5.3163. Min Act: -0.0000

Data Index: 18169 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 6.4911. Min Range: -6.4911

Max Act: 5.4636. Min Act: -0.0000

Data Index: 1355125 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.9767. Min Act: -0.0000

Data Index: 1176563 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 6.4911. Min Range: -6.4911

Max Act: 5.1334. Min Act: -0.0000

Data Index: 1339726 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 6.4911. Min Range: -6.4911

Max Act: 5.1231. Min Act: -0.0000

Data Index: 377620 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 6.4911. Min Range: -6.4911

Max Act: 5.1828. Min Act: -0.0000

Data Index: 174923 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.7203. Min Act: -0.0000

Data Index: 541326 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.5728. Min Act: -0.0000

Data Index: 934795 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.8066. Min Act: -0.0000

Data Index: 789551 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.5855. Min Act: -0.0000

Data Index: 805026 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.9547. Min Act: -0.0000

Data Index: 360407 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.5539. Min Act: -0.0000

Data Index: 558042 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.6393. Min Act: -0.0000

Data Index: 832778 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.6598. Min Act: -0.0000

Data Index: 1159892 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.5931. Min Act: -0.0000

Data Index: 309167 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.1584. Min Act: -0.0000

Data Index: 59273 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 6.4911. Min Range: -6.4911

Max Act: 4.1871. Min Act: -0.0000

Data Index: 142132 (C4 (Web Text))

Max Activating Token Index: 1014