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

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

Neuron 4736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3892. Min Range: -2.3892

Max Act: 2.3892. Min Act: -0.0000

Data Index: 419308 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 2.3892. Min Range: -2.3892

Max Act: 2.1513. Min Act: -0.0000

Data Index: 118493 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 2.3892. Min Range: -2.3892

Max Act: 2.2182. Min Act: -0.0000

Data Index: 1337260 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.3892. Min Range: -2.3892

Max Act: 2.1221. Min Act: -0.0000

Data Index: 717639 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.9421. Min Act: -0.0000

Data Index: 95100 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 2.3892. Min Range: -2.3892

Max Act: 2.1462. Min Act: -0.0000

Data Index: 264713 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 2.3892. Min Range: -2.3892

Max Act: 2.2452. Min Act: -0.0000

Data Index: 1008357 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.9164. Min Act: -0.0000

Data Index: 585283 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.8807. Min Act: -0.0000

Data Index: 1162435 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.8408. Min Act: -0.0000

Data Index: 183586 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.8000. Min Act: -0.0000

Data Index: 636394 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.8933. Min Act: -0.0000

Data Index: 663400 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.7680. Min Act: -0.0000

Data Index: 579701 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.8737. Min Act: -0.0000

Data Index: 513205 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.9368. Min Act: -0.0000

Data Index: 301141 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.7217. Min Act: -0.0000

Data Index: 899540 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.7207. Min Act: -0.0000

Data Index: 566281 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.6745. Min Act: -0.0000

Data Index: 508635 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.5401. Min Act: -0.0000

Data Index: 222341 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.3892. Min Range: -2.3892

Max Act: 1.8454. Min Act: -0.0000

Data Index: 1244245 (C4 (Web Text))

Max Activating Token Index: 369