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

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

Neuron 1479 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: 0.4361. Min Range: -0.4361

Max Act: 0.4270. Min Act: -0.0000

Data Index: 95456 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.4361. Min Act: -0.0000

Data Index: 198494 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.4240. Min Act: -0.0000

Data Index: 618451 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1022817 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.4121. Min Act: -0.0000

Data Index: 660710 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.4030. Min Act: -0.0000

Data Index: 515798 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3995. Min Act: -0.0000

Data Index: 48546 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.4100. Min Act: -0.0000

Data Index: 619396 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.4044. Min Act: -0.0000

Data Index: 577853 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3674. Min Act: -0.0000

Data Index: 611203 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3916. Min Act: -0.0000

Data Index: 503187 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3623. Min Act: -0.0000

Data Index: 456150 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1325676 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3301. Min Act: -0.0000

Data Index: 39112 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3409. Min Act: -0.0000

Data Index: 802204 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3059. Min Act: -0.0000

Data Index: 52982 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1035548 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1323858 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3205. Min Act: -0.0000

Data Index: 849439 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.4361. Min Range: -0.4361

Max Act: 0.3165. Min Act: -0.0000

Data Index: 373491 (C4 (Web Text))

Max Activating Token Index: 978