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

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

Neuron 5336 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: 3.6721. Min Range: -3.6721

Max Act: 3.6721. Min Act: -0.0001

Data Index: 444844 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.0413. Min Act: -0.0001

Data Index: 1227019 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.2605. Min Act: -0.0001

Data Index: 1250513 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.0480. Min Act: -0.0000

Data Index: 210277 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.7607. Min Act: -0.0000

Data Index: 1001802 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.8931. Min Act: -0.0001

Data Index: 350058 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.7110. Min Act: -0.0000

Data Index: 1348613 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.5583. Min Act: -0.0000

Data Index: 767792 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.6680. Min Act: -0.0000

Data Index: 87989 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.4304. Min Act: -0.0001

Data Index: 544276 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.4328. Min Act: -0.0000

Data Index: 5311 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.5289. Min Act: -0.0001

Data Index: 712165 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.6603. Min Act: -0.0000

Data Index: 153035 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.4930. Min Act: -0.0000

Data Index: 723129 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.6587. Min Act: -0.0000

Data Index: 1248847 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.3428. Min Act: -0.0000

Data Index: 1332080 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.3850. Min Act: -0.0000

Data Index: 642567 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.3925. Min Act: -0.0000

Data Index: 278017 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.3007. Min Act: -0.0000

Data Index: 718308 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 3.6721. Min Range: -3.6721

Max Act: 2.3740. Min Act: -0.0001

Data Index: 340577 (C4 (Web Text))

Max Activating Token Index: 105