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

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

Neuron 4353 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.5936. Min Act: -0.0002

Data Index: 136315 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.6424. Min Act: -0.0002

Data Index: 1160536 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.5549. Min Act: -0.0002

Data Index: 662821 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.5974. Min Act: -0.0002

Data Index: 1109963 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.5552. Min Act: -0.0002

Data Index: 361417 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.3987. Min Act: -0.0002

Data Index: 313775 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.4410. Min Act: -0.0002

Data Index: 378277 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.4387. Min Act: -0.0002

Data Index: 1113269 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.5950. Min Act: -0.0002

Data Index: 497335 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.5536. Min Act: -0.0002

Data Index: 991899 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.4405. Min Act: -0.0002

Data Index: 1015993 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.3634. Min Act: -0.0002

Data Index: 601070 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.4615. Min Act: -0.0002

Data Index: 1237724 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.3845. Min Act: -0.0002

Data Index: 385337 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.5513. Min Act: -0.0002

Data Index: 325849 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.4597. Min Act: -0.0002

Data Index: 1271215 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.4443. Min Act: -0.0002

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.4384. Min Act: -0.0002

Data Index: 461418 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.3149. Min Act: -0.0002

Data Index: 658636 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.6424. Min Range: -1.6424

Max Act: 1.3858. Min Act: -0.0002

Data Index: 977 (C4 (Web Text))

Max Activating Token Index: 181