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

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

Neuron 3644 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8970. Min Act: -0.0000

Data Index: 200363 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8706. Min Act: -0.0000

Data Index: 249698 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7979. Min Act: -0.0000

Data Index: 217676 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7930. Min Act: -0.0000

Data Index: 832137 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1172215 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6834. Min Act: -0.0000

Data Index: 358564 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6972. Min Act: -0.0000

Data Index: 831569 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7216. Min Act: -0.0000

Data Index: 80857 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7320. Min Act: -0.0000

Data Index: 818268 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6628. Min Act: -0.0000

Data Index: 292825 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6681. Min Act: -0.0000

Data Index: 313479 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6765. Min Act: -0.0000

Data Index: 931722 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1321570 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1358318 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6297. Min Act: -0.0000

Data Index: 913774 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1311900 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6461. Min Act: -0.0000

Data Index: 322020 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6531. Min Act: -0.0000

Data Index: 131795 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1031207 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6244. Min Act: -0.0000

Data Index: 693462 (C4 (Web Text))

Max Activating Token Index: 188