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

Dataset: The Pile

Neuron 4891 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: 1.0968. Min Range: -1.0968

Max Act: 1.0487. Min Act: -0.0000

Data Index: 257116 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1560426 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0158. Min Act: -0.0000

Data Index: 716175 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1737023 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1232031 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 1.0968. Min Range: -1.0968

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1362048 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1127106 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9204. Min Act: -0.0000

Data Index: 793561 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9832. Min Act: -0.0000

Data Index: 114537 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.8830. Min Act: -0.0000

Data Index: 212745 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1123046 (The Pile)

Max Activating Token Index: 268

Text #11

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1021706 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9223. Min Act: -0.0000

Data Index: 124303 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9844. Min Act: -0.0000

Data Index: 52697 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9059. Min Act: -0.0000

Data Index: 407838 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1587199 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9296. Min Act: -0.0000

Data Index: 540912 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1740470 (The Pile)

Max Activating Token Index: 844

Text #18

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1544734 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 1.0968. Min Range: -1.0968

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1335146 (The Pile)

Max Activating Token Index: 314