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

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

Neuron 662 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5001. Min Range: -4.5001

Max Act: 4.5001. Min Act: -0.0000

Data Index: 891977 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 4.5001. Min Range: -4.5001

Max Act: 4.2254. Min Act: -0.0000

Data Index: 340978 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 4.5001. Min Range: -4.5001

Max Act: 4.1380. Min Act: -0.0000

Data Index: 175288 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.9584. Min Act: -0.0000

Data Index: 192889 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.8509. Min Act: -0.0000

Data Index: 22261 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.9139. Min Act: -0.0000

Data Index: 1228080 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.6668. Min Act: -0.0000

Data Index: 951072 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.5351. Min Act: -0.0000

Data Index: 18003 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.2362. Min Act: -0.0000

Data Index: 830224 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.2793. Min Act: -0.0000

Data Index: 385563 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.4376. Min Act: -0.0000

Data Index: 661205 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.2677. Min Act: -0.0000

Data Index: 522536 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.0795. Min Act: -0.0000

Data Index: 1290637 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.2261. Min Act: -0.0000

Data Index: 660289 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.0546. Min Act: -0.0000

Data Index: 402821 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.1939. Min Act: -0.0000

Data Index: 1072839 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.1510. Min Act: -0.0000

Data Index: 317208 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.1478. Min Act: -0.0000

Data Index: 1083549 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.0671. Min Act: -0.0000

Data Index: 1260294 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 4.5001. Min Range: -4.5001

Max Act: 3.0659. Min Act: -0.0000

Data Index: 197101 (C4 (Web Text))

Max Activating Token Index: 813