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

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

Neuron 3560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.8645. Min Act: -0.0000

Data Index: 450536 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.9152. Min Act: -0.0000

Data Index: 230658 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.7610. Min Act: -0.0000

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.7475. Min Act: -0.0000

Data Index: 106665 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.7145. Min Act: -0.0000

Data Index: 82265 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.8027. Min Act: -0.0000

Data Index: 1279453 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.6520. Min Act: -0.0000

Data Index: 6947 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.6174. Min Act: -0.0000

Data Index: 1252098 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.6017. Min Act: -0.0000

Data Index: 58351 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.5090. Min Act: -0.0000

Data Index: 892842 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.5203. Min Act: -0.0000

Data Index: 346539 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.5234. Min Act: -0.0000

Data Index: 719654 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.4318. Min Act: -0.0000

Data Index: 357444 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.5146. Min Act: -0.0000

Data Index: 741164 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.4502. Min Act: -0.0000

Data Index: 316963 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.4482. Min Act: -0.0000

Data Index: 103550 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.3661. Min Act: -0.0000

Data Index: 367551 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.3235. Min Act: -0.0000

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.3621. Min Act: -0.0000

Data Index: 34639 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 1.9152. Min Range: -1.9152

Max Act: 1.3276. Min Act: -0.0000

Data Index: 54893 (C4 (Web Text))

Max Activating Token Index: 979