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

Dataset: The Pile

Neuron 255 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4965. Min Act: -0.0000

Data Index: 1538101 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.6367. Min Act: -0.0000

Data Index: 623187 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1622437 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4475. Min Act: -0.0000

Data Index: 1599187 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5403. Min Act: -0.0000

Data Index: 1165584 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4020. Min Act: -0.0000

Data Index: 469366 (The Pile)

Max Activating Token Index: 892

Text #6

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3886. Min Act: -0.0000

Data Index: 120731 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3046. Min Act: -0.0000

Data Index: 1819337 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5503. Min Act: -0.0000

Data Index: 394462 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.5499. Min Act: -0.0000

Data Index: 547570 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4297. Min Act: -0.0000

Data Index: 432933 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4554. Min Act: -0.0000

Data Index: 1837011 (The Pile)

Max Activating Token Index: 686

Text #12

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3475. Min Act: -0.0000

Data Index: 1772893 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4168. Min Act: -0.0000

Data Index: 165122 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.4277. Min Act: -0.0000

Data Index: 655610 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3107. Min Act: -0.0000

Data Index: 946493 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.2914. Min Act: -0.0000

Data Index: 495938 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3584. Min Act: -0.0000

Data Index: 600991 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1929599 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 1.6367. Min Range: -1.6367

Max Act: 1.2505. Min Act: -0.0000

Data Index: 440341 (The Pile)

Max Activating Token Index: 929