Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2343 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3166. Min Range: -1.3166

Max Act: 1.3166. Min Act: -0.0001

Data Index: 1162422 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.8194. Min Act: -0.0001

Data Index: 997300 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.8360. Min Act: -0.0001

Data Index: 1069558 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.8243. Min Act: -0.0002

Data Index: 754476 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.8020. Min Act: -0.0001

Data Index: 948349 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7896. Min Act: -0.0002

Data Index: 453614 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1205116 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7747. Min Act: -0.0002

Data Index: 547709 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7680. Min Act: -0.0001

Data Index: 681560 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7159. Min Act: -0.0002

Data Index: 1028553 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7520. Min Act: -0.0001

Data Index: 3533 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7147. Min Act: -0.0002

Data Index: 434822 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7019. Min Act: -0.0001

Data Index: 385871 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7456. Min Act: -0.0001

Data Index: 429540 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.7537. Min Act: -0.0001

Data Index: 112619 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.6531. Min Act: -0.0001

Data Index: 7982 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.6958. Min Act: -0.0002

Data Index: 727104 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.6674. Min Act: -0.0002

Data Index: 953399 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.6464. Min Act: -0.0002

Data Index: 1272763 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 1.3166. Min Range: -1.3166

Max Act: 0.6685. Min Act: -0.0001

Data Index: 492523 (C4 (Web Text))

Max Activating Token Index: 327