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

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

Neuron 3343 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.7579. Min Range: -10.7579

Max Act: 10.7579. Min Act: -0.0001

Data Index: 581223 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 10.7579. Min Range: -10.7579

Max Act: 9.0791. Min Act: -0.0001

Data Index: 304982 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 10.7579. Min Range: -10.7579

Max Act: 8.3293. Min Act: -0.0001

Data Index: 414877 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 10.7579. Min Range: -10.7579

Max Act: 8.3010. Min Act: -0.0001

Data Index: 685458 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 10.7579. Min Range: -10.7579

Max Act: 7.9049. Min Act: -0.0001

Data Index: 1050712 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 10.7579. Min Range: -10.7579

Max Act: 7.8799. Min Act: -0.0001

Data Index: 578299 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 10.7579. Min Range: -10.7579

Max Act: 7.6973. Min Act: -0.0001

Data Index: 1329415 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 10.7579. Min Range: -10.7579

Max Act: 8.6065. Min Act: -0.0001

Data Index: 191097 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 10.7579. Min Range: -10.7579

Max Act: 7.1635. Min Act: -0.0001

Data Index: 326125 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 10.7579. Min Range: -10.7579

Max Act: 7.0323. Min Act: -0.0001

Data Index: 832058 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 10.7579. Min Range: -10.7579

Max Act: 5.0787. Min Act: -0.0001

Data Index: 573616 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 10.7579. Min Range: -10.7579

Max Act: 4.5781. Min Act: -0.0001

Data Index: 127987 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 10.7579. Min Range: -10.7579

Max Act: 3.7988. Min Act: -0.0001

Data Index: 895494 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 10.7579. Min Range: -10.7579

Max Act: 3.3142. Min Act: -0.0000

Data Index: 549159 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 10.7579. Min Range: -10.7579

Max Act: 2.5033. Min Act: -0.0001

Data Index: 1008568 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 10.7579. Min Range: -10.7579

Max Act: 2.7708. Min Act: -0.0001

Data Index: 60845 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 10.7579. Min Range: -10.7579

Max Act: 2.6729. Min Act: -0.0001

Data Index: 901928 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 10.7579. Min Range: -10.7579

Max Act: 2.9213. Min Act: -0.0001

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 10.7579. Min Range: -10.7579

Max Act: 2.2386. Min Act: -0.0000

Data Index: 229639 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 10.7579. Min Range: -10.7579

Max Act: 2.5911. Min Act: -0.0001

Data Index: 523574 (C4 (Web Text))

Max Activating Token Index: 112