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

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

Neuron 287 in Layer 0

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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 318715 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 1166945 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 692173 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 425880 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 763206 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 801445 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 284439 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 961282 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 261280 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 473816 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 845689 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0001

Data Index: 552865 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 418218 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 691197 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1275803 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1149204 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 352194 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1273845 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1455439 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 137047 (C4 (Web Text))

Max Activating Token Index: 106