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

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

Neuron 4804 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2669. Min Range: -2.2669

Max Act: 2.2669. Min Act: -0.0000

Data Index: 1121804 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.9373. Min Act: -0.0000

Data Index: 77936 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 2.2669. Min Range: -2.2669

Max Act: 2.1995. Min Act: -0.0001

Data Index: 1268420 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 2.2669. Min Range: -2.2669

Max Act: 2.0508. Min Act: -0.0000

Data Index: 5359 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.9142. Min Act: -0.0001

Data Index: 1347641 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.7936. Min Act: -0.0000

Data Index: 842356 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6820. Min Act: -0.0000

Data Index: 1023475 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.8583. Min Act: -0.0000

Data Index: 277607 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6349. Min Act: -0.0001

Data Index: 1162997 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.7954. Min Act: -0.0000

Data Index: 1105500 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6164. Min Act: -0.0000

Data Index: 11319 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6963. Min Act: -0.0001

Data Index: 982887 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.5745. Min Act: -0.0000

Data Index: 511686 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.5541. Min Act: -0.0001

Data Index: 891938 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.5530. Min Act: -0.0000

Data Index: 87435 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6246. Min Act: -0.0001

Data Index: 1018059 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6152. Min Act: -0.0000

Data Index: 677600 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6096. Min Act: -0.0000

Data Index: 1061979 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.6779. Min Act: -0.0000

Data Index: 132853 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 2.2669. Min Range: -2.2669

Max Act: 1.5739. Min Act: -0.0000

Data Index: 726165 (C4 (Web Text))

Max Activating Token Index: 71