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

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

Neuron 72 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.1031. Min Act: -0.0000

Data Index: 291984 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8802. Min Act: -0.0000

Data Index: 976530 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9199. Min Act: -0.0000

Data Index: 340141 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1238948 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.6795. Min Act: -0.0000

Data Index: 621619 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7879. Min Act: -0.0000

Data Index: 721006 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8027. Min Act: -0.0000

Data Index: 989194 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7320. Min Act: -0.0000

Data Index: 655637 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7831. Min Act: -0.0000

Data Index: 178495 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7301. Min Act: -0.0000

Data Index: 784366 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8222. Min Act: -0.0000

Data Index: 904859 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7414. Min Act: -0.0000

Data Index: 75791 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7436. Min Act: -0.0000

Data Index: 626466 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1050529 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7916. Min Act: -0.0000

Data Index: 528159 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.6280. Min Act: -0.0000

Data Index: 119905 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7099. Min Act: -0.0000

Data Index: 711645 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.6871. Min Act: -0.0000

Data Index: 33454 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7076. Min Act: -0.0000

Data Index: 392548 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7023. Min Act: -0.0000

Data Index: 542288 (C4 (Web Text))

Max Activating Token Index: 677