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

Dataset: The Pile

Neuron 4000 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1106542 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1830419 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1861194 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1470. Min Act: -0.0000

Data Index: 730384 (The Pile)

Max Activating Token Index: 555

Text #4

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1118. Min Act: -0.0000

Data Index: 435883 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1305. Min Act: -0.0000

Data Index: 716175 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1574. Min Act: -0.0000

Data Index: 297984 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1897979 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1345235 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0352. Min Act: -0.0000

Data Index: 639216 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1364. Min Act: -0.0000

Data Index: 247796 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1402408 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0521. Min Act: -0.0000

Data Index: 275623 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0559. Min Act: -0.0000

Data Index: 494276 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.9952. Min Act: -0.0000

Data Index: 790507 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0166. Min Act: -0.0000

Data Index: 995309 (The Pile)

Max Activating Token Index: 914

Text #16

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1485558 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1170454 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 1.2554. Min Range: -1.2554

Max Act: 1.0247. Min Act: -0.0000

Data Index: 782807 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.2554. Min Range: -1.2554

Max Act: 0.9569. Min Act: -0.0000

Data Index: 92636 (The Pile)

Max Activating Token Index: 509