Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 864 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.2172. Min Act: -0.0001

Data Index: 960401 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1234163 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1846. Min Act: -0.0001

Data Index: 588625 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1817. Min Act: -0.0001

Data Index: 465436 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1763. Min Act: -0.0001

Data Index: 936305 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1685. Min Act: -0.0001

Data Index: 212626 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1607. Min Act: -0.0001

Data Index: 132485 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1330. Min Act: -0.0001

Data Index: 637650 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1566. Min Act: -0.0001

Data Index: 948338 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1519. Min Act: -0.0001

Data Index: 97488 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1577. Min Act: -0.0001

Data Index: 706558 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1649. Min Act: -0.0001

Data Index: 300177 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1572. Min Act: -0.0001

Data Index: 96111 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1552. Min Act: -0.0001

Data Index: 69493 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1429. Min Act: -0.0001

Data Index: 321335 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1493. Min Act: -0.0001

Data Index: 672596 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1044943 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1406. Min Act: -0.0001

Data Index: 295408 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1237. Min Act: -0.0001

Data Index: 931412 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1123843 (C4 (Web Text))

Max Activating Token Index: 521