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

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

Neuron 2953 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: 1.7737. Min Range: -1.7737

Max Act: 1.5429. Min Act: -0.0001

Data Index: 1174392 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.7737. Min Act: -0.0001

Data Index: 930353 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.6763. Min Act: -0.0001

Data Index: 326412 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5708. Min Act: -0.0001

Data Index: 130606 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5860. Min Act: -0.0001

Data Index: 436202 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.6197. Min Act: -0.0001

Data Index: 956821 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4956. Min Act: -0.0001

Data Index: 875926 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5813. Min Act: -0.0002

Data Index: 1214225 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5666. Min Act: -0.0001

Data Index: 492026 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4689. Min Act: -0.0001

Data Index: 960626 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.5283. Min Act: -0.0001

Data Index: 1028084 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4634. Min Act: -0.0001

Data Index: 488195 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4881. Min Act: -0.0001

Data Index: 877060 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4436. Min Act: -0.0001

Data Index: 776443 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3476. Min Act: -0.0002

Data Index: 1112779 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4750. Min Act: -0.0001

Data Index: 147827 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3966. Min Act: -0.0002

Data Index: 1313740 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.3876. Min Act: -0.0002

Data Index: 576681 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.2802. Min Act: -0.0001

Data Index: 1553157 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 1.7737. Min Range: -1.7737

Max Act: 1.4280. Min Act: -0.0001

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 381