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

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

Neuron 1592 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.7849. Min Act: -0.0001

Data Index: 594874 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.6178. Min Act: -0.0001

Data Index: 1283587 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5831. Min Act: -0.0001

Data Index: 1159197 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5844. Min Act: -0.0001

Data Index: 206331 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5827. Min Act: -0.0001

Data Index: 164726 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.4816. Min Act: -0.0001

Data Index: 1008720 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5470. Min Act: -0.0001

Data Index: 385618 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5630. Min Act: -0.0001

Data Index: 547427 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5554. Min Act: -0.0001

Data Index: 150208 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5408. Min Act: -0.0001

Data Index: 995188 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.4956. Min Act: -0.0001

Data Index: 277443 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5500. Min Act: -0.0001

Data Index: 160229 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5148. Min Act: -0.0001

Data Index: 707513 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5383. Min Act: -0.0001

Data Index: 778533 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5011. Min Act: -0.0001

Data Index: 1223500 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5020. Min Act: -0.0001

Data Index: 42810 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5522. Min Act: -0.0001

Data Index: 961333 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5082. Min Act: -0.0001

Data Index: 1338431 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5548. Min Act: -0.0001

Data Index: 683404 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.7849. Min Range: -0.7849

Max Act: 0.5131. Min Act: -0.0001

Data Index: 156671 (C4 (Web Text))

Max Activating Token Index: 206