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

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

Neuron 5126 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0324. Min Range: -2.0324

Max Act: 2.0324. Min Act: -0.0000

Data Index: 649804 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.7243. Min Act: -0.0000

Data Index: 1348473 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6292. Min Act: -0.0001

Data Index: 906850 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.8918. Min Act: -0.0001

Data Index: 246070 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.5852. Min Act: -0.0001

Data Index: 220066 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6687. Min Act: -0.0001

Data Index: 80320 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.5695. Min Act: -0.0001

Data Index: 593874 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6483. Min Act: -0.0001

Data Index: 489188 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.7995. Min Act: -0.0000

Data Index: 1185636 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6969. Min Act: -0.0000

Data Index: 619811 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6603. Min Act: -0.0001

Data Index: 1045789 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1033464 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.5700. Min Act: -0.0001

Data Index: 278690 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.7476. Min Act: -0.0000

Data Index: 948784 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.8647. Min Act: -0.0000

Data Index: 1251177 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6782. Min Act: -0.0001

Data Index: 144537 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1234796 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6196. Min Act: -0.0000

Data Index: 1319177 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.5121. Min Act: -0.0001

Data Index: 184241 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 2.0324. Min Range: -2.0324

Max Act: 1.6005. Min Act: -0.0001

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 534