Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 348 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.7296. Min Act: -0.0001

Data Index: 814621 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5699. Min Act: -0.0001

Data Index: 14001 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5441. Min Act: -0.0001

Data Index: 839030 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5173. Min Act: -0.0001

Data Index: 1357153 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5347. Min Act: -0.0001

Data Index: 355719 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5291. Min Act: -0.0001

Data Index: 510868 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5005. Min Act: -0.0001

Data Index: 804429 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4791. Min Act: -0.0001

Data Index: 31523 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4523. Min Act: -0.0001

Data Index: 116071 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4830. Min Act: -0.0001

Data Index: 920912 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4760. Min Act: -0.0001

Data Index: 326535 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4758. Min Act: -0.0001

Data Index: 548500 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4759. Min Act: -0.0001

Data Index: 1306812 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4724. Min Act: -0.0001

Data Index: 173412 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4548. Min Act: -0.0001

Data Index: 136464 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4450. Min Act: -0.0001

Data Index: 903489 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4613. Min Act: -0.0001

Data Index: 1259173 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4619. Min Act: -0.0001

Data Index: 1254019 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4452. Min Act: -0.0001

Data Index: 983451 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4750. Min Act: -0.0001

Data Index: 766756 (C4 (Web Text))

Max Activating Token Index: 1004