Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1069836 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3155. Min Act: -0.0000

Data Index: 255199 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.3337. Min Act: -0.0000

Data Index: 779895 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2319. Min Act: -0.0000

Data Index: 1448510 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2140. Min Act: -0.0000

Data Index: 54627 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1706676 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1164609 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2022. Min Act: -0.0000

Data Index: 1166769 (The Pile)

Max Activating Token Index: 514

Text #8

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1309. Min Act: -0.0000

Data Index: 94794 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1527344 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1415. Min Act: -0.0000

Data Index: 564933 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1461. Min Act: -0.0000

Data Index: 613208 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1807. Min Act: -0.0000

Data Index: 616301 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1543872 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1232091 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1658. Min Act: -0.0000

Data Index: 1264383 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1582. Min Act: -0.0000

Data Index: 258899 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1229414 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1928961 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1874947 (The Pile)

Max Activating Token Index: 783