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

Dataset: The Pile

Neuron 3269 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1506014 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4484. Min Act: -0.0000

Data Index: 610249 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1920819 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1149537 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3817. Min Act: -0.0000

Data Index: 989409 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3803. Min Act: -0.0000

Data Index: 453531 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3589. Min Act: -0.0000

Data Index: 334550 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3819. Min Act: -0.0000

Data Index: 416059 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3827. Min Act: -0.0000

Data Index: 538472 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1945993 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3518. Min Act: -0.0000

Data Index: 29422 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1085760 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3734. Min Act: -0.0000

Data Index: 762944 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3451. Min Act: -0.0000

Data Index: 227267 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3489. Min Act: -0.0000

Data Index: 716757 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1947424 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3518. Min Act: -0.0000

Data Index: 764227 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3298. Min Act: -0.0000

Data Index: 949033 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3247. Min Act: -0.0000

Data Index: 364044 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1305855 (The Pile)

Max Activating Token Index: 297