Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1895 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0004

Data Index: 74825 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0413. Min Act: -0.0004

Data Index: 512635 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0445. Min Act: -0.0004

Data Index: 435408 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0420. Min Act: -0.0004

Data Index: 195460 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0441. Min Act: -0.0004

Data Index: 120011 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0417. Min Act: -0.0004

Data Index: 458604 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0431. Min Act: -0.0004

Data Index: 576644 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0450. Min Act: -0.0004

Data Index: 1173295 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0416. Min Act: -0.0004

Data Index: 443845 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0414. Min Act: -0.0004

Data Index: 646646 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0424. Min Act: -0.0004

Data Index: 733723 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0438. Min Act: -0.0004

Data Index: 530238 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0416. Min Act: -0.0004

Data Index: 1231238 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0415. Min Act: -0.0004

Data Index: 1029081 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0398. Min Act: -0.0004

Data Index: 135003 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0419. Min Act: -0.0004

Data Index: 778555 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0381. Min Act: -0.0004

Data Index: 668729 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0398. Min Act: -0.0004

Data Index: 927523 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0414. Min Act: -0.0004

Data Index: 1282352 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0358. Min Act: -0.0004

Data Index: 866688 (C4 (Web Text))

Max Activating Token Index: 321