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

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

Neuron 5044 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: 0.9323. Min Range: -0.9323

Max Act: 0.9323. Min Act: -0.0001

Data Index: 576428 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.9070. Min Act: -0.0001

Data Index: 562601 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1151253 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8687. Min Act: -0.0001

Data Index: 766867 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8694. Min Act: -0.0001

Data Index: 1080583 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8522. Min Act: -0.0001

Data Index: 700608 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8400. Min Act: -0.0001

Data Index: 508843 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8474. Min Act: -0.0001

Data Index: 1186050 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8467. Min Act: -0.0001

Data Index: 1112725 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8487. Min Act: -0.0001

Data Index: 1087679 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8332. Min Act: -0.0001

Data Index: 2025 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8322. Min Act: -0.0001

Data Index: 61959 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8461. Min Act: -0.0001

Data Index: 187609 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8344. Min Act: -0.0001

Data Index: 814640 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8176. Min Act: -0.0001

Data Index: 454445 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8203. Min Act: -0.0002

Data Index: 927306 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8410. Min Act: -0.0001

Data Index: 945909 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1350304 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8173. Min Act: -0.0001

Data Index: 108995 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8215. Min Act: -0.0001

Data Index: 135190 (C4 (Web Text))

Max Activating Token Index: 125