Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4171 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.2049. Min Act: -0.0001

Data Index: 75901 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1902. Min Act: -0.0001

Data Index: 258677 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1799. Min Act: -0.0001

Data Index: 176192 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1779. Min Act: -0.0001

Data Index: 187912 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1789. Min Act: -0.0001

Data Index: 611321 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1037259 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1758. Min Act: -0.0001

Data Index: 611938 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1224354 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1229589 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1479. Min Act: -0.0001

Data Index: 18921 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1534. Min Act: -0.0001

Data Index: 213228 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1523. Min Act: -0.0001

Data Index: 87815 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1545. Min Act: -0.0001

Data Index: 729666 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1550. Min Act: -0.0001

Data Index: 729751 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1234621 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1444. Min Act: -0.0001

Data Index: 99267 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1464. Min Act: -0.0001

Data Index: 932089 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1137446 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1392. Min Act: -0.0001

Data Index: 926654 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1549. Min Act: -0.0001

Data Index: 79790 (C4 (Web Text))

Max Activating Token Index: 297