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

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

Neuron 3282 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.6421. Min Act: -0.0000

Data Index: 93159 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.6950. Min Act: -0.0000

Data Index: 1068270 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.5528. Min Act: -0.0000

Data Index: 34635 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.6148. Min Act: -0.0000

Data Index: 1044140 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4521. Min Act: 0.0000

Data Index: 570668 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4314. Min Act: -0.0000

Data Index: 2345 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4832. Min Act: 0.0000

Data Index: 1183278 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.5756. Min Act: -0.0000

Data Index: 414946 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4785. Min Act: 0.0000

Data Index: 1222282 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4789. Min Act: 0.0000

Data Index: 299326 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4523. Min Act: -0.0000

Data Index: 1274537 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4216. Min Act: -0.0000

Data Index: 539457 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.5200. Min Act: -0.0000

Data Index: 58828 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.5110. Min Act: -0.0000

Data Index: 70213 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4103. Min Act: -0.0000

Data Index: 301589 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4172. Min Act: 0.0000

Data Index: 870848 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.4220. Min Act: 0.0000

Data Index: 1323822 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.3973. Min Act: 0.0000

Data Index: 909599 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.3836. Min Act: 0.0000

Data Index: 683937 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.3662. Min Act: -0.0000

Data Index: 932662 (C4 (Web Text))

Max Activating Token Index: 907