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

Dataset: The Pile

Neuron 2991 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: 0.2815. Min Range: -0.2815

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1455881 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1812830 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1428316 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1040274 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1524780 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1521743 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1993049 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2589. Min Act: -0.0000

Data Index: 889310 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2504. Min Act: -0.0000

Data Index: 91515 (The Pile)

Max Activating Token Index: 100

Text #9

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1744314 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1190232 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1920306 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2461. Min Act: -0.0000

Data Index: 917253 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2361. Min Act: -0.0000

Data Index: 466683 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1784059 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2248. Min Act: -0.0000

Data Index: 367352 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2293. Min Act: -0.0000

Data Index: 473538 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2123. Min Act: -0.0000

Data Index: 478189 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1494711 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1254360 (The Pile)

Max Activating Token Index: 226