Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2753 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1685231 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3943. Min Act: -0.0000

Data Index: 264913 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3921. Min Act: -0.0000

Data Index: 147249 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2942. Min Act: -0.0000

Data Index: 734231 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2421. Min Act: -0.0000

Data Index: 218147 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1358057 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3214. Min Act: -0.0000

Data Index: 546877 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1319362 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1035480 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3479. Min Act: -0.0000

Data Index: 1421339 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3265. Min Act: -0.0000

Data Index: 365767 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2144. Min Act: -0.0000

Data Index: 842251 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2351. Min Act: -0.0000

Data Index: 313536 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1787373 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1927. Min Act: -0.0000

Data Index: 1425609 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1484. Min Act: -0.0000

Data Index: 507020 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0584. Min Act: -0.0000

Data Index: 461984 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1444089 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1362446 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2740. Min Act: -0.0000

Data Index: 898293 (The Pile)

Max Activating Token Index: 1016