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

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

Neuron 1119 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5849. Min Act: -0.0000

Data Index: 280675 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5046. Min Act: -0.0000

Data Index: 275716 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5443. Min Act: -0.0000

Data Index: 936152 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5410. Min Act: -0.0000

Data Index: 923788 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5533. Min Act: -0.0000

Data Index: 112132 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1437370 (Python Code)

Max Activating Token Index: 930

Text #6

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1425861 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5019. Min Act: -0.0000

Data Index: 734458 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4820. Min Act: -0.0000

Data Index: 458689 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1587155 (Python Code)

Max Activating Token Index: 809

Text #10

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1464098 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4927. Min Act: -0.0000

Data Index: 115789 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1226949 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1003830 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1079428 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4526. Min Act: -0.0000

Data Index: 174477 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1291735 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4225. Min Act: -0.0000

Data Index: 383636 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1578073 (Python Code)

Max Activating Token Index: 845

Text #19

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4814. Min Act: -0.0000

Data Index: 999730 (C4 (Web Text))

Max Activating Token Index: 410