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

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

Neuron 4846 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: 1.1370. Min Range: -1.1370

Max Act: 1.1370. Min Act: -0.0002

Data Index: 1291463 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.1349. Min Act: -0.0002

Data Index: 175379 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0731. Min Act: -0.0002

Data Index: 448836 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0492. Min Act: -0.0002

Data Index: 113212 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0191. Min Act: -0.0002

Data Index: 934721 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0055. Min Act: -0.0002

Data Index: 1001247 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9894. Min Act: -0.0002

Data Index: 65939 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9793. Min Act: -0.0002

Data Index: 156444 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9555. Min Act: -0.0002

Data Index: 446239 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9637. Min Act: -0.0002

Data Index: 1219830 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9370. Min Act: -0.0002

Data Index: 761789 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9408. Min Act: -0.0002

Data Index: 961001 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9547. Min Act: -0.0002

Data Index: 976639 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9456. Min Act: -0.0002

Data Index: 966617 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9319. Min Act: -0.0002

Data Index: 1163445 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9195. Min Act: -0.0003

Data Index: 1160651 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9300. Min Act: -0.0002

Data Index: 1288885 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9203. Min Act: -0.0002

Data Index: 517963 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9125. Min Act: -0.0002

Data Index: 62302 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9056. Min Act: -0.0002

Data Index: 451024 (C4 (Web Text))

Max Activating Token Index: 151