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

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

Neuron 3628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.7900. Min Act: -0.0000

Data Index: 187582 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.7401. Min Act: -0.0001

Data Index: 673375 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6360. Min Act: -0.0000

Data Index: 172371 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6336. Min Act: -0.0001

Data Index: 1016908 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5639. Min Act: -0.0001

Data Index: 1306853 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1024086 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5767. Min Act: -0.0001

Data Index: 1296470 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5405. Min Act: -0.0001

Data Index: 833175 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5464. Min Act: -0.0001

Data Index: 881927 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1049608 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5398. Min Act: -0.0001

Data Index: 709983 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5332. Min Act: -0.0001

Data Index: 257544 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5450. Min Act: -0.0001

Data Index: 609206 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5421. Min Act: -0.0001

Data Index: 803372 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.4977. Min Act: -0.0001

Data Index: 1350469 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5100. Min Act: -0.0001

Data Index: 436161 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.4934. Min Act: -0.0000

Data Index: 452480 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5203. Min Act: -0.0001

Data Index: 1199104 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5007. Min Act: -0.0001

Data Index: 1209250 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.4801. Min Act: -0.0000

Data Index: 960092 (C4 (Web Text))

Max Activating Token Index: 891