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

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

Neuron 350 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: 2.9892. Min Range: -2.9892

Max Act: 2.9892. Min Act: -0.0000

Data Index: 936951 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.8514. Min Act: -0.0000

Data Index: 684912 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.8744. Min Act: -0.0000

Data Index: 780023 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.9459. Min Act: -0.0000

Data Index: 540640 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.6564. Min Act: -0.0000

Data Index: 26498 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.6464. Min Act: -0.0000

Data Index: 522308 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.7316. Min Act: -0.0000

Data Index: 606320 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.3332. Min Act: -0.0000

Data Index: 928939 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.5794. Min Act: -0.0000

Data Index: 977125 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.5236. Min Act: -0.0000

Data Index: 277298 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.4754. Min Act: -0.0000

Data Index: 322822 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.5989. Min Act: -0.0000

Data Index: 579634 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.5861. Min Act: -0.0000

Data Index: 1294539 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.4269. Min Act: -0.0000

Data Index: 1258080 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.4122. Min Act: -0.0000

Data Index: 194104 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.4044. Min Act: -0.0000

Data Index: 1032549 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.3766. Min Act: -0.0000

Data Index: 540448 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.3780. Min Act: -0.0000

Data Index: 580833 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.3644. Min Act: -0.0000

Data Index: 759148 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 2.9892. Min Range: -2.9892

Max Act: 2.2275. Min Act: -0.0000

Data Index: 1344431 (C4 (Web Text))

Max Activating Token Index: 645