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

Dataset: The Pile

Neuron 4066 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2786. Min Act: -0.0000

Data Index: 286548 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1632343 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1704932 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1454231 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1181278 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1527812 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1614251 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1267041 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2215. Min Act: -0.0000

Data Index: 466947 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1298634 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1825735 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1194171 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1347778 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1551362 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1157757 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2157. Min Act: -0.0000

Data Index: 643059 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.1938. Min Act: -0.0000

Data Index: 930475 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2020. Min Act: -0.0000

Data Index: 938893 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.2017. Min Act: -0.0000

Data Index: 591356 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 0.2786. Min Range: -0.2786

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1494548 (The Pile)

Max Activating Token Index: 335