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

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

Neuron 2973 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1406481 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1406793 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1531613 (Python Code)

Max Activating Token Index: 966

Text #3

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1076364 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1431888 (Python Code)

Max Activating Token Index: 915

Text #5

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.5109. Min Act: -0.0000

Data Index: 349026 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1394384 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4786. Min Act: -0.0000

Data Index: 520318 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4817. Min Act: -0.0000

Data Index: 481644 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4924. Min Act: -0.0000

Data Index: 854185 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4279. Min Act: -0.0000

Data Index: 713714 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4538. Min Act: -0.0000

Data Index: 313346 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1542044 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4638. Min Act: -0.0000

Data Index: 920170 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4639. Min Act: -0.0000

Data Index: 304017 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4226. Min Act: -0.0000

Data Index: 857689 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4407. Min Act: -0.0000

Data Index: 187266 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4280. Min Act: -0.0000

Data Index: 852027 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1595736 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 0.6577. Min Range: -0.6577

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1226958 (C4 (Web Text))

Max Activating Token Index: 478