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

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

Neuron 2546 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1684. Min Range: -1.1684

Max Act: 1.1684. Min Act: -0.0003

Data Index: 1534630 (Python Code)

Max Activating Token Index: 722

Text #1

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9750. Min Act: -0.0003

Data Index: 1470766 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9462. Min Act: -0.0003

Data Index: 1491188 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9683. Min Act: -0.0003

Data Index: 1546052 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8813. Min Act: -0.0003

Data Index: 1393085 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8764. Min Act: -0.0003

Data Index: 1651114 (Python Code)

Max Activating Token Index: 567

Text #6

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9443. Min Act: -0.0003

Data Index: 1598166 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9172. Min Act: -0.0003

Data Index: 1560934 (Python Code)

Max Activating Token Index: 775

Text #8

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8671. Min Act: -0.0003

Data Index: 1560148 (Python Code)

Max Activating Token Index: 433

Text #9

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9340. Min Act: -0.0003

Data Index: 1546773 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8747. Min Act: -0.0003

Data Index: 1504959 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9307. Min Act: -0.0003

Data Index: 1651739 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8748. Min Act: -0.0003

Data Index: 1625752 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8979. Min Act: -0.0003

Data Index: 1553809 (Python Code)

Max Activating Token Index: 908

Text #14

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8697. Min Act: -0.0003

Data Index: 1545085 (Python Code)

Max Activating Token Index: 690

Text #15

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9316. Min Act: -0.0003

Data Index: 1433340 (Python Code)

Max Activating Token Index: 659

Text #16

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.9230. Min Act: -0.0003

Data Index: 1599090 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.7879. Min Act: -0.0003

Data Index: 1562631 (Python Code)

Max Activating Token Index: 550

Text #18

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8248. Min Act: -0.0003

Data Index: 1498633 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 1.1684. Min Range: -1.1684

Max Act: 0.8217. Min Act: -0.0003

Data Index: 1562086 (Python Code)

Max Activating Token Index: 389