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

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

Neuron 2021 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.6117. Min Act: -0.0000

Data Index: 453917 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.6249. Min Act: -0.0000

Data Index: 981148 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.6208. Min Act: -0.0000

Data Index: 918844 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.5508. Min Act: -0.0000

Data Index: 129022 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.5076. Min Act: -0.0000

Data Index: 1011584 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.2845. Min Act: -0.0000

Data Index: 877436 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.2845. Min Act: -0.0000

Data Index: 785172 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.5088. Min Act: -0.0000

Data Index: 698512 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.3623. Min Act: -0.0000

Data Index: 1117233 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.1437. Min Act: -0.0000

Data Index: 827183 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.4207. Min Act: -0.0000

Data Index: 1000208 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.2473. Min Act: -0.0000

Data Index: 388647 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.2459. Min Act: -0.0000

Data Index: 735910 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.1884. Min Act: -0.0000

Data Index: 1293731 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.1650. Min Act: -0.0000

Data Index: 320802 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.2633. Min Act: -0.0000

Data Index: 444603 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.0333. Min Act: -0.0000

Data Index: 617603 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.0970. Min Act: -0.0000

Data Index: 476586 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 2.6249. Min Range: -2.6249

Max Act: 1.9796. Min Act: -0.0000

Data Index: 735899 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 2.6249. Min Range: -2.6249

Max Act: 2.0314. Min Act: -0.0000

Data Index: 1215178 (C4 (Web Text))

Max Activating Token Index: 934