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

Dataset: The Pile

Neuron 1369 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1040896 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.5339. Min Act: 0.0000

Data Index: 1347434 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1954037 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.5254. Min Act: -0.0000

Data Index: 164182 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1306111 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3876. Min Act: -0.0000

Data Index: 567025 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.4299. Min Act: -0.0000

Data Index: 762456 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2889. Min Act: -0.0000

Data Index: 1650755 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2455. Min Act: -0.0000

Data Index: 983821 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3601. Min Act: -0.0000

Data Index: 948169 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2026. Min Act: -0.0000

Data Index: 153605 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1370877 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.1786. Min Act: -0.0000

Data Index: 570098 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2163. Min Act: 0.0000

Data Index: 1387770 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.3215. Min Act: -0.0000

Data Index: 913535 (The Pile)

Max Activating Token Index: 756

Text #15

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1847323 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1846286 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.2833. Min Act: -0.0000

Data Index: 531009 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.1197. Min Act: 0.0000

Data Index: 842103 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 1.5339. Min Range: -1.5339

Max Act: 1.1193. Min Act: -0.0000

Data Index: 470188 (The Pile)

Max Activating Token Index: 704