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

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

Neuron 479 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1388296 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6777. Min Act: -0.0000

Data Index: 958635 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1553309 (Python Code)

Max Activating Token Index: 400

Text #3

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1454274 (Python Code)

Max Activating Token Index: 561

Text #4

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1567074 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6401. Min Act: -0.0000

Data Index: 223135 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1436479 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1518623 (Python Code)

Max Activating Token Index: 530

Text #8

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1416390 (Python Code)

Max Activating Token Index: 912

Text #9

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1486310 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1386080 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1414218 (Python Code)

Max Activating Token Index: 502

Text #12

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1400791 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1511269 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1656033 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1492906 (Python Code)

Max Activating Token Index: 703

Text #16

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1638564 (Python Code)

Max Activating Token Index: 566

Text #17

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1384488 (Python Code)

Max Activating Token Index: 470

Text #18

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1584827 (Python Code)

Max Activating Token Index: 782

Text #19

Max Range: 0.7856. Min Range: -0.7856

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1577657 (Python Code)

Max Activating Token Index: 617