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

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

Neuron 570 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: 1.1902. Min Range: -1.1902

Max Act: 1.0159. Min Act: -0.0001

Data Index: 444638 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1902. Min Act: -0.0001

Data Index: 1035173 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8779. Min Act: -0.0001

Data Index: 5537 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9618. Min Act: -0.0001

Data Index: 1218109 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8570. Min Act: -0.0001

Data Index: 1125209 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9150. Min Act: -0.0001

Data Index: 442707 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8647. Min Act: -0.0001

Data Index: 1185358 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8529. Min Act: -0.0001

Data Index: 498030 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9069. Min Act: -0.0001

Data Index: 169975 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0313. Min Act: -0.0001

Data Index: 185536 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7997. Min Act: -0.0001

Data Index: 771554 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1062588 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8486. Min Act: -0.0001

Data Index: 1142423 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8440. Min Act: -0.0001

Data Index: 513622 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7647. Min Act: -0.0001

Data Index: 1198695 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7506. Min Act: -0.0001

Data Index: 533950 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7586. Min Act: -0.0001

Data Index: 141258 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8219. Min Act: -0.0001

Data Index: 1541330 (Python Code)

Max Activating Token Index: 412

Text #18

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8430. Min Act: -0.0001

Data Index: 389946 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8732. Min Act: -0.0001

Data Index: 491606 (C4 (Web Text))

Max Activating Token Index: 182