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

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

Neuron 840 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0001

Data Index: 718548 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1865. Min Act: -0.0000

Data Index: 288599 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1736. Min Act: -0.0000

Data Index: 735182 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1305775 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1711. Min Act: -0.0001

Data Index: 673803 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1770. Min Act: -0.0000

Data Index: 64745 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1584. Min Act: -0.0000

Data Index: 790397 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1348752 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1601. Min Act: -0.0000

Data Index: 394432 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1706. Min Act: -0.0001

Data Index: 432704 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1088515 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1557. Min Act: -0.0000

Data Index: 475322 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1664. Min Act: -0.0001

Data Index: 200672 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1228892 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1547. Min Act: -0.0000

Data Index: 431131 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1185190 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1538. Min Act: -0.0001

Data Index: 843827 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1431. Min Act: -0.0000

Data Index: 259156 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1465. Min Act: -0.0001

Data Index: 292244 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1407. Min Act: -0.0000

Data Index: 589495 (C4 (Web Text))

Max Activating Token Index: 440