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

Dataset: The Pile

Neuron 3039 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: 0.6674. Min Range: -0.6674

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1739589 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.6674. Min Act: -0.0000

Data Index: 299052 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5984. Min Act: -0.0000

Data Index: 356636 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1486283 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1564163 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5394. Min Act: -0.0000

Data Index: 489443 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1054741 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1289512 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1218669 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1420088 (The Pile)

Max Activating Token Index: 838

Text #10

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1128433 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1646977 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1003202 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4863. Min Act: -0.0000

Data Index: 335988 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5179. Min Act: -0.0000

Data Index: 559502 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1963655 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1231320 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1425883 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1477146 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 0.6674. Min Range: -0.6674

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1218543 (The Pile)

Max Activating Token Index: 973