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

Dataset: The Pile

Neuron 1373 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1376333 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2747. Min Act: -0.0000

Data Index: 477782 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1743705 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2258. Min Act: -0.0000

Data Index: 549695 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2381. Min Act: -0.0000

Data Index: 8956 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2443. Min Act: -0.0000

Data Index: 441713 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2169. Min Act: -0.0000

Data Index: 332334 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1177116 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1142710 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1986316 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1187840 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2202. Min Act: -0.0000

Data Index: 942151 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2265. Min Act: -0.0000

Data Index: 168933 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2125. Min Act: -0.0000

Data Index: 415745 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1521062 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2092. Min Act: -0.0000

Data Index: 869931 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1211688 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.1773. Min Act: -0.0000

Data Index: 549838 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2302. Min Act: -0.0000

Data Index: 985428 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1685936 (The Pile)

Max Activating Token Index: 507