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

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

Neuron 1131 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.9524. Min Act: -0.0000

Data Index: 390222 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.9872. Min Act: -0.0000

Data Index: 378294 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8573. Min Act: -0.0000

Data Index: 150196 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8735. Min Act: -0.0000

Data Index: 901856 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7823. Min Act: -0.0000

Data Index: 873383 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8350. Min Act: -0.0000

Data Index: 183404 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7753. Min Act: -0.0000

Data Index: 604509 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7325. Min Act: -0.0000

Data Index: 953054 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7511. Min Act: -0.0000

Data Index: 710195 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7201. Min Act: -0.0000

Data Index: 384710 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7053. Min Act: -0.0000

Data Index: 447501 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7691. Min Act: -0.0000

Data Index: 169145 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6923. Min Act: -0.0000

Data Index: 589053 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6501. Min Act: -0.0000

Data Index: 818538 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6253. Min Act: -0.0000

Data Index: 716303 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1126867 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6343. Min Act: -0.0000

Data Index: 907045 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6569. Min Act: -0.0000

Data Index: 670954 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.6137. Min Act: -0.0000

Data Index: 154345 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.5416. Min Act: -0.0000

Data Index: 299815 (C4 (Web Text))

Max Activating Token Index: 365