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

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

Neuron 2482 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: 0.6967. Min Range: -0.6967

Max Act: 0.6967. Min Act: -0.0000

Data Index: 224568 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5317. Min Act: -0.0000

Data Index: 199913 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.5192. Min Act: -0.0000

Data Index: 698254 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4818. Min Act: -0.0000

Data Index: 385231 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4829. Min Act: -0.0000

Data Index: 276264 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4741. Min Act: -0.0000

Data Index: 196681 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4639. Min Act: -0.0000

Data Index: 601451 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1014544 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4761. Min Act: -0.0000

Data Index: 853751 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4509. Min Act: -0.0000

Data Index: 889718 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4171. Min Act: -0.0000

Data Index: 190451 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1156332 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4414. Min Act: -0.0000

Data Index: 307622 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1175597 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4377. Min Act: -0.0000

Data Index: 112842 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4432. Min Act: -0.0000

Data Index: 682007 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4374. Min Act: -0.0000

Data Index: 17559 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4211. Min Act: -0.0000

Data Index: 335019 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4513. Min Act: -0.0000

Data Index: 813612 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.6967. Min Range: -0.6967

Max Act: 0.4373. Min Act: -0.0000

Data Index: 678799 (C4 (Web Text))

Max Activating Token Index: 163