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

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

Neuron 2448 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: 0.6485. Min Range: -0.6485

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1313687 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5984. Min Act: 0.0000

Data Index: 1203237 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5683. Min Act: -0.0000

Data Index: 326997 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.5480. Min Act: -0.0000

Data Index: 867646 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4881. Min Act: -0.0000

Data Index: 380022 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4891. Min Act: 0.0000

Data Index: 1070227 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1057091 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1164744 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4347. Min Act: -0.0000

Data Index: 157150 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1208329 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4476. Min Act: -0.0000

Data Index: 893777 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4544. Min Act: -0.0000

Data Index: 15249 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4157. Min Act: -0.0000

Data Index: 813168 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1265435 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1117422 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1262476 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4078. Min Act: -0.0000

Data Index: 983113 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4437. Min Act: -0.0000

Data Index: 128919 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4036. Min Act: -0.0000

Data Index: 694674 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.6485. Min Range: -0.6485

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1129346 (C4 (Web Text))

Max Activating Token Index: 825