Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3238 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8825. Min Act: -0.0002

Data Index: 356194 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7900. Min Act: -0.0003

Data Index: 955090 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7894. Min Act: -0.0002

Data Index: 153399 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7647. Min Act: -0.0002

Data Index: 553506 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7440. Min Act: -0.0002

Data Index: 319600 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7253. Min Act: -0.0002

Data Index: 629443 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7179. Min Act: -0.0002

Data Index: 519494 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7142. Min Act: -0.0002

Data Index: 1078008 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7261. Min Act: -0.0002

Data Index: 362108 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7022. Min Act: -0.0002

Data Index: 677297 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7056. Min Act: -0.0003

Data Index: 420243 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6757. Min Act: -0.0002

Data Index: 1243560 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6731. Min Act: -0.0002

Data Index: 583293 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6630. Min Act: -0.0002

Data Index: 99995 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6438. Min Act: -0.0002

Data Index: 1235038 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6517. Min Act: -0.0002

Data Index: 609119 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6312. Min Act: -0.0002

Data Index: 817638 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6232. Min Act: -0.0002

Data Index: 666180 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6189. Min Act: -0.0002

Data Index: 1012273 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6108. Min Act: -0.0003

Data Index: 298684 (C4 (Web Text))

Max Activating Token Index: 201