Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1896 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0285. Min Range: -1.0285

Max Act: 1.0285. Min Act: -0.0001

Data Index: 979313 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.9730. Min Act: -0.0001

Data Index: 573382 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.9704. Min Act: -0.0001

Data Index: 204314 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.9165. Min Act: -0.0001

Data Index: 1343402 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.9026. Min Act: -0.0001

Data Index: 124900 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.8208. Min Act: -0.0001

Data Index: 1221690 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.8453. Min Act: -0.0001

Data Index: 1155045 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.8051. Min Act: -0.0001

Data Index: 462737 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.8263. Min Act: -0.0001

Data Index: 962699 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1068976 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7833. Min Act: -0.0001

Data Index: 730820 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.8083. Min Act: -0.0001

Data Index: 172843 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.8089. Min Act: -0.0001

Data Index: 894953 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7691. Min Act: -0.0001

Data Index: 856392 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.8013. Min Act: -0.0001

Data Index: 425506 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7392. Min Act: -0.0001

Data Index: 151458 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7410. Min Act: -0.0001

Data Index: 196317 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7348. Min Act: -0.0001

Data Index: 1328232 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7284. Min Act: -0.0001

Data Index: 1233761 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7570. Min Act: -0.0001

Data Index: 283266 (C4 (Web Text))

Max Activating Token Index: 816