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

Dataset: The Pile

Neuron 2485 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6330. Min Range: -3.6330

Max Act: 3.6330. Min Act: -0.0000

Data Index: 695045 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.9205. Min Act: -0.0000

Data Index: 167045 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.9365. Min Act: -0.0000

Data Index: 796346 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.7529. Min Act: -0.0000

Data Index: 1503099 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.7862. Min Act: -0.0000

Data Index: 1518658 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.6258. Min Act: -0.0000

Data Index: 384257 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.4370. Min Act: -0.0000

Data Index: 956543 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.2768. Min Act: -0.0000

Data Index: 1406511 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.5780. Min Act: -0.0000

Data Index: 1105855 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.3058. Min Act: -0.0000

Data Index: 453728 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.4172. Min Act: -0.0000

Data Index: 197655 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.4180. Min Act: -0.0000

Data Index: 950663 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.3577. Min Act: -0.0000

Data Index: 1754552 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.3067. Min Act: -0.0000

Data Index: 149685 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.6895. Min Act: -0.0000

Data Index: 1951422 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.1668. Min Act: -0.0000

Data Index: 1693536 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.1549. Min Act: -0.0000

Data Index: 230932 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.9377. Min Act: -0.0000

Data Index: 1506742 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.3842. Min Act: -0.0000

Data Index: 1871121 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.0317. Min Act: -0.0000

Data Index: 1933906 (The Pile)

Max Activating Token Index: 478