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

Dataset: The Pile

Neuron 4289 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0930. Min Range: -5.0930

Max Act: 5.0498. Min Act: -0.0000

Data Index: 1448361 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 5.0930. Min Range: -5.0930

Max Act: 5.0772. Min Act: -0.0000

Data Index: 1310179 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.6363. Min Act: -0.0000

Data Index: 73449 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 5.0930. Min Range: -5.0930

Max Act: 5.0930. Min Act: -0.0000

Data Index: 514862 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.6951. Min Act: -0.0000

Data Index: 1175346 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.2261. Min Act: -0.0000

Data Index: 652911 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.4866. Min Act: -0.0000

Data Index: 328138 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.4871. Min Act: -0.0000

Data Index: 1567350 (The Pile)

Max Activating Token Index: 458

Text #8

Max Range: 5.0930. Min Range: -5.0930

Max Act: 3.9532. Min Act: -0.0000

Data Index: 1708776 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.0938. Min Act: -0.0000

Data Index: 1745265 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.0440. Min Act: -0.0000

Data Index: 726142 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.1984. Min Act: -0.0000

Data Index: 464963 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.5383. Min Act: -0.0000

Data Index: 37942 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.1486. Min Act: -0.0000

Data Index: 1338725 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.1551. Min Act: -0.0000

Data Index: 252409 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 5.0930. Min Range: -5.0930

Max Act: 3.9207. Min Act: -0.0000

Data Index: 1655283 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 5.0930. Min Range: -5.0930

Max Act: 3.9409. Min Act: -0.0000

Data Index: 689891 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 5.0930. Min Range: -5.0930

Max Act: 3.8934. Min Act: -0.0000

Data Index: 1156823 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 5.0930. Min Range: -5.0930

Max Act: 3.9635. Min Act: -0.0000

Data Index: 1643641 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 5.0930. Min Range: -5.0930

Max Act: 4.0385. Min Act: -0.0000

Data Index: 735188 (The Pile)

Max Activating Token Index: 554