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

Dataset: The Pile

Neuron 1626 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3298. Min Act: -0.0000

Data Index: 275805 (The Pile)

Max Activating Token Index: 813

Text #1

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3116. Min Act: -0.0000

Data Index: 235248 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1126390 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1980071 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3006. Min Act: -0.0000

Data Index: 970181 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.3017. Min Act: -0.0000

Data Index: 207626 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1136840 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1339047 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1903489 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2569. Min Act: -0.0000

Data Index: 543245 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2716. Min Act: -0.0000

Data Index: 7830 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2641. Min Act: -0.0000

Data Index: 717588 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2530. Min Act: -0.0000

Data Index: 867911 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1220586 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2476. Min Act: -0.0000

Data Index: 197440 (The Pile)

Max Activating Token Index: 563

Text #15

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1894440 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2458. Min Act: 0.0000

Data Index: 1363287 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1633984 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1844699 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.3298. Min Range: -0.3298

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1288207 (The Pile)

Max Activating Token Index: 248