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

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

Neuron 4192 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: 0.8502. Min Range: -0.8502

Max Act: 0.8502. Min Act: -0.0002

Data Index: 1079245 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.8135. Min Act: -0.0002

Data Index: 31245 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.8201. Min Act: -0.0002

Data Index: 551912 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.8102. Min Act: -0.0002

Data Index: 1257126 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.8037. Min Act: -0.0003

Data Index: 1336353 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7891. Min Act: -0.0002

Data Index: 189430 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.8084. Min Act: -0.0002

Data Index: 1189846 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7749. Min Act: -0.0002

Data Index: 1156914 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7750. Min Act: -0.0002

Data Index: 528105 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7652. Min Act: -0.0002

Data Index: 563750 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7637. Min Act: -0.0002

Data Index: 1287832 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7643. Min Act: -0.0002

Data Index: 398804 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7523. Min Act: -0.0002

Data Index: 2521 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7412. Min Act: -0.0002

Data Index: 770284 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7642. Min Act: -0.0002

Data Index: 1133266 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7418. Min Act: -0.0002

Data Index: 498053 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7756. Min Act: -0.0002

Data Index: 237468 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7428. Min Act: -0.0002

Data Index: 1311944 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7513. Min Act: -0.0002

Data Index: 288549 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7434. Min Act: -0.0002

Data Index: 795506 (C4 (Web Text))

Max Activating Token Index: 685