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

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

Neuron 2228 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: 0.5365. Min Range: -0.5365

Max Act: 0.5365. Min Act: -0.0002

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.5251. Min Act: -0.0002

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.5052. Min Act: -0.0002

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.5035. Min Act: -0.0002

Data Index: 832381 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4937. Min Act: -0.0002

Data Index: 1536881 (Python Code)

Max Activating Token Index: 577

Text #5

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4679. Min Act: -0.0002

Data Index: 835850 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4546. Min Act: -0.0002

Data Index: 1241736 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4516. Min Act: -0.0002

Data Index: 1406621 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4514. Min Act: -0.0002

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4561. Min Act: -0.0002

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4387. Min Act: -0.0002

Data Index: 1476876 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4375. Min Act: -0.0002

Data Index: 906418 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4262. Min Act: -0.0002

Data Index: 1314596 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4321. Min Act: -0.0002

Data Index: 1586811 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4173. Min Act: -0.0002

Data Index: 370341 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4148. Min Act: -0.0002

Data Index: 1532706 (Python Code)

Max Activating Token Index: 580

Text #16

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4278. Min Act: -0.0002

Data Index: 231741 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4172. Min Act: -0.0002

Data Index: 1467460 (Python Code)

Max Activating Token Index: 493

Text #18

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4186. Min Act: -0.0002

Data Index: 1643684 (Python Code)

Max Activating Token Index: 984

Text #19

Max Range: 0.5365. Min Range: -0.5365

Max Act: 0.4117. Min Act: -0.0002

Data Index: 1501105 (Python Code)

Max Activating Token Index: 755