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

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

Neuron 1735 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: 1.9307. Min Range: -1.9307

Max Act: 1.8680. Min Act: -0.0000

Data Index: 474031 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.9307. Min Act: -0.0000

Data Index: 238306 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.5213. Min Act: -0.0000

Data Index: 778772 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1160863 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.7199. Min Act: -0.0000

Data Index: 177279 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.5526. Min Act: -0.0000

Data Index: 421203 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.4485. Min Act: -0.0000

Data Index: 557831 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.5176. Min Act: -0.0000

Data Index: 39708 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.5961. Min Act: -0.0000

Data Index: 761361 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.4915. Min Act: -0.0000

Data Index: 581388 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.6115. Min Act: -0.0000

Data Index: 1159205 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.5054. Min Act: -0.0000

Data Index: 278442 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.3717. Min Act: -0.0000

Data Index: 1078339 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.3042. Min Act: -0.0000

Data Index: 489555 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1316736 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.3796. Min Act: -0.0000

Data Index: 576889 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1563146 (Python Code)

Max Activating Token Index: 648

Text #17

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1129822 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.3213. Min Act: -0.0000

Data Index: 966624 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.9307. Min Range: -1.9307

Max Act: 1.2245. Min Act: -0.0000

Data Index: 136431 (C4 (Web Text))

Max Activating Token Index: 633