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

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

Neuron 5242 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: 1.1442. Min Range: -1.1442

Max Act: 1.1442. Min Act: -0.0002

Data Index: 1134185 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9762. Min Act: -0.0002

Data Index: 51701 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9620. Min Act: -0.0002

Data Index: 162382 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9465. Min Act: -0.0002

Data Index: 855627 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9296. Min Act: -0.0002

Data Index: 1174213 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9351. Min Act: -0.0002

Data Index: 551614 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9377. Min Act: -0.0002

Data Index: 524974 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9344. Min Act: -0.0002

Data Index: 462619 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9152. Min Act: -0.0002

Data Index: 1163122 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9059. Min Act: -0.0003

Data Index: 493629 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.9022. Min Act: -0.0002

Data Index: 899035 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8929. Min Act: -0.0002

Data Index: 157922 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8886. Min Act: -0.0002

Data Index: 217979 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8580. Min Act: -0.0002

Data Index: 779100 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8712. Min Act: -0.0002

Data Index: 251426 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8555. Min Act: -0.0002

Data Index: 142503 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8606. Min Act: -0.0002

Data Index: 34052 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8544. Min Act: -0.0002

Data Index: 642847 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8485. Min Act: -0.0002

Data Index: 435443 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8602. Min Act: -0.0002

Data Index: 957217 (C4 (Web Text))

Max Activating Token Index: 264