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

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

Neuron 3249 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.1599. Min Act: -0.0001

Data Index: 1320977 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.1499. Min Act: -0.0001

Data Index: 77253 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.0530. Min Act: -0.0001

Data Index: 669552 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.0114. Min Act: -0.0001

Data Index: 466627 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.1599. Min Range: -1.1599

Max Act: 1.0050. Min Act: -0.0001

Data Index: 534043 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9539. Min Act: -0.0001

Data Index: 640045 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9130. Min Act: -0.0001

Data Index: 563760 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9708. Min Act: -0.0001

Data Index: 235027 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9407. Min Act: -0.0001

Data Index: 1221801 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9548. Min Act: -0.0001

Data Index: 918060 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9178. Min Act: -0.0001

Data Index: 802363 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8335. Min Act: -0.0001

Data Index: 543347 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9056. Min Act: -0.0001

Data Index: 1237032 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8985. Min Act: -0.0001

Data Index: 113829 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9166. Min Act: -0.0001

Data Index: 306937 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8741. Min Act: -0.0001

Data Index: 511641 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8564. Min Act: -0.0001

Data Index: 496214 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.8328. Min Act: -0.0001

Data Index: 305681 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9127. Min Act: -0.0001

Data Index: 530327 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.1599. Min Range: -1.1599

Max Act: 0.9041. Min Act: -0.0001

Data Index: 531923 (C4 (Web Text))

Max Activating Token Index: 413