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

Dataset: The Pile

Neuron 2932 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.8784. Min Act: -0.0000

Data Index: 950431 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.8392. Min Act: -0.0000

Data Index: 1276451 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1951824 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.6766. Min Act: -0.0000

Data Index: 888312 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.6536. Min Act: -0.0000

Data Index: 842181 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.7428. Min Act: -0.0000

Data Index: 168162 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1606298 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.6001. Min Act: -0.0000

Data Index: 477490 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1493393 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.7381. Min Act: -0.0000

Data Index: 920542 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5879. Min Act: -0.0000

Data Index: 1114980 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.6277. Min Act: -0.0000

Data Index: 515089 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.7046. Min Act: -0.0000

Data Index: 326894 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5555. Min Act: -0.0000

Data Index: 321337 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5171. Min Act: -0.0000

Data Index: 80444 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5709. Min Act: -0.0000

Data Index: 602531 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5181. Min Act: -0.0000

Data Index: 22171 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5619. Min Act: -0.0000

Data Index: 570863 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5269. Min Act: -0.0000

Data Index: 1765989 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1638866 (The Pile)

Max Activating Token Index: 328