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

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

Neuron 3698 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1619522 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1068004 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7454. Min Act: -0.0000

Data Index: 143116 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7467. Min Act: -0.0001

Data Index: 1045590 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6546. Min Act: -0.0000

Data Index: 806429 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1065455 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6185. Min Act: -0.0001

Data Index: 1136320 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6407. Min Act: -0.0001

Data Index: 525009 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6077. Min Act: -0.0001

Data Index: 836657 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1629797 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6263. Min Act: -0.0000

Data Index: 332805 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5823. Min Act: -0.0000

Data Index: 74663 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5547. Min Act: -0.0001

Data Index: 75526 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6093. Min Act: -0.0001

Data Index: 161267 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1547260 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1066732 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5744. Min Act: -0.0001

Data Index: 910152 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5531. Min Act: -0.0001

Data Index: 383858 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1200879 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.5582. Min Act: -0.0001

Data Index: 134064 (C4 (Web Text))

Max Activating Token Index: 201