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

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

Neuron 2206 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6567. Min Act: -0.0001

Data Index: 539012 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5462. Min Act: -0.0001

Data Index: 517332 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6332. Min Act: -0.0002

Data Index: 386241 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4238. Min Act: -0.0001

Data Index: 1618815 (Python Code)

Max Activating Token Index: 600

Text #4

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5773. Min Act: -0.0002

Data Index: 1057739 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5262. Min Act: -0.0001

Data Index: 586167 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5530. Min Act: -0.0001

Data Index: 959614 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6767. Min Act: -0.0002

Data Index: 500763 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5768. Min Act: -0.0001

Data Index: 658961 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5180. Min Act: -0.0001

Data Index: 520 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5148. Min Act: -0.0001

Data Index: 1109194 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5387. Min Act: -0.0001

Data Index: 872336 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4845. Min Act: -0.0002

Data Index: 1017172 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5653. Min Act: -0.0002

Data Index: 739220 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3404. Min Act: -0.0001

Data Index: 742354 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4015. Min Act: -0.0001

Data Index: 872619 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5553. Min Act: -0.0001

Data Index: 196894 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6297. Min Act: -0.0001

Data Index: 308758 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5350. Min Act: -0.0002

Data Index: 253687 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5350. Min Act: -0.0001

Data Index: 912027 (C4 (Web Text))

Max Activating Token Index: 5