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

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

Neuron 4825 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1096158 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4837. Min Act: -0.0000

Data Index: 731936 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1092556 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4457. Min Act: -0.0001

Data Index: 667972 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4929. Min Act: -0.0001

Data Index: 519231 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1131584 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4970. Min Act: -0.0001

Data Index: 290951 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1188364 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4624. Min Act: -0.0000

Data Index: 741727 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4759. Min Act: -0.0000

Data Index: 647142 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4431. Min Act: -0.0000

Data Index: 951343 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.3957. Min Act: -0.0001

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4383. Min Act: -0.0001

Data Index: 426799 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4158. Min Act: -0.0000

Data Index: 574546 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4511. Min Act: -0.0001

Data Index: 411772 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4041. Min Act: -0.0001

Data Index: 1228754 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4189. Min Act: -0.0001

Data Index: 1237020 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4015. Min Act: -0.0000

Data Index: 454441 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.6947. Min Range: -0.6947

Max Act: 0.4296. Min Act: -0.0001

Data Index: 1040604 (C4 (Web Text))

Max Activating Token Index: 534