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

Dataset: The Pile

Neuron 1209 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: 1.1465. Min Range: -1.1465

Max Act: 1.1465. Min Act: -0.0000

Data Index: 334248 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 1.1465. Min Range: -1.1465

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1743713 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9755. Min Act: -0.0000

Data Index: 543656 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1928534 (The Pile)

Max Activating Token Index: 328

Text #4

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1921601 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1711105 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1126170 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8944. Min Act: -0.0000

Data Index: 819868 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1793721 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1317954 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8503. Min Act: -0.0000

Data Index: 25687 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8715. Min Act: -0.0000

Data Index: 921846 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8656. Min Act: -0.0000

Data Index: 326690 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1856705 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8550. Min Act: -0.0000

Data Index: 277999 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8797. Min Act: -0.0000

Data Index: 846809 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1318376 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8785. Min Act: -0.0000

Data Index: 450967 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.8251. Min Act: -0.0000

Data Index: 41629 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 1.1465. Min Range: -1.1465

Max Act: 0.7426. Min Act: -0.0000

Data Index: 494931 (The Pile)

Max Activating Token Index: 983