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

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

Neuron 4404 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: 3.6215. Min Range: -3.6215

Max Act: 3.6215. Min Act: -0.0001

Data Index: 59029 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.1808. Min Act: -0.0000

Data Index: 978678 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.2943. Min Act: -0.0000

Data Index: 736316 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.4566. Min Act: -0.0000

Data Index: 1093481 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.3357. Min Act: -0.0001

Data Index: 711807 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.1790. Min Act: -0.0000

Data Index: 717672 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.1194. Min Act: -0.0001

Data Index: 1157266 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.7640. Min Act: -0.0000

Data Index: 59632 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.8899. Min Act: -0.0001

Data Index: 852971 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.5827. Min Act: -0.0000

Data Index: 185944 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.9973. Min Act: -0.0000

Data Index: 268952 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.8300. Min Act: -0.0001

Data Index: 693932 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.9635. Min Act: -0.0000

Data Index: 1202751 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.7842. Min Act: -0.0000

Data Index: 1124054 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.5639. Min Act: -0.0000

Data Index: 192441 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.8083. Min Act: -0.0000

Data Index: 294900 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.6442. Min Act: -0.0001

Data Index: 143015 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.5729. Min Act: -0.0001

Data Index: 54455 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 3.6215. Min Range: -3.6215

Max Act: 1.9883. Min Act: -0.0000

Data Index: 5029 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 3.6215. Min Range: -3.6215

Max Act: 2.6917. Min Act: -0.0000

Data Index: 1088053 (C4 (Web Text))

Max Activating Token Index: 217