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

Dataset: The Pile

Neuron 1873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1563394 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1245931 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1347449 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2353. Min Act: -0.0000

Data Index: 492394 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2343. Min Act: -0.0000

Data Index: 180320 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1072624 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2199. Min Act: -0.0000

Data Index: 220781 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2358. Min Act: -0.0000

Data Index: 691355 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1752560 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2195. Min Act: -0.0000

Data Index: 913274 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1838426 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2257. Min Act: -0.0000

Data Index: 81992 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2034. Min Act: 0.0000

Data Index: 931329 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1052965 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2062. Min Act: -0.0000

Data Index: 619080 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.2035. Min Act: -0.0000

Data Index: 608912 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1059949 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1767878 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1578910 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 0.2723. Min Range: -0.2723

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1278542 (The Pile)

Max Activating Token Index: 155