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

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

Neuron 6113 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.8487. Min Act: 0.0000

Data Index: 92044 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.7317. Min Act: -0.0000

Data Index: 51928 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.6266. Min Act: -0.0000

Data Index: 217670 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.4469. Min Act: -0.0000

Data Index: 116493 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5092. Min Act: 0.0000

Data Index: 792140 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.4809. Min Act: -0.0000

Data Index: 1287007 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1060963 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.4351. Min Act: 0.0000

Data Index: 231371 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1155840 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1068284 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3718. Min Act: -0.0000

Data Index: 278699 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1106182 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3555. Min Act: -0.0000

Data Index: 1037400 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1045560 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3571. Min Act: -0.0000

Data Index: 27991 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.2440. Min Act: -0.0000

Data Index: 248532 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1092848 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1339178 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.2835. Min Act: -0.0000

Data Index: 160477 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1209576 (C4 (Web Text))

Max Activating Token Index: 75