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

Dataset: The Pile

Neuron 1088 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.7943. Min Act: 0.0000

Data Index: 229578 (The Pile)

Max Activating Token Index: 830

Text #1

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.7369. Min Act: -0.0000

Data Index: 474881 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.7315. Min Act: -0.0000

Data Index: 877405 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6754. Min Act: -0.0000

Data Index: 750647 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6772. Min Act: -0.0000

Data Index: 387677 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.7478. Min Act: -0.0000

Data Index: 264920 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6382. Min Act: -0.0000

Data Index: 850626 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5198. Min Act: -0.0000

Data Index: 509318 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.4910. Min Act: 0.0000

Data Index: 1268883 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.4879. Min Act: -0.0000

Data Index: 847239 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1064908 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.4461. Min Act: -0.0000

Data Index: 814300 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.3081. Min Act: -0.0000

Data Index: 273253 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5329. Min Act: -0.0000

Data Index: 1209458 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.3543. Min Act: -0.0000

Data Index: 785712 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.3530. Min Act: -0.0000

Data Index: 547698 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1144837 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.4078. Min Act: 0.0000

Data Index: 1455243 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.3845. Min Act: -0.0000

Data Index: 1359992 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.3679. Min Act: -0.0000

Data Index: 827656 (The Pile)

Max Activating Token Index: 776