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

Dataset: The Pile

Neuron 3634 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1998172 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1484218 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1348363 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4101. Min Act: -0.0000

Data Index: 458361 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3886. Min Act: -0.0000

Data Index: 839766 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3758. Min Act: -0.0000

Data Index: 877080 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1263998 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3970. Min Act: -0.0000

Data Index: 351363 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1241395 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4067. Min Act: -0.0000

Data Index: 301279 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1153552 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1846699 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4042. Min Act: -0.0000

Data Index: 952663 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1782864 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1747940 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3677. Min Act: -0.0000

Data Index: 264994 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1551321 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1156939 (The Pile)

Max Activating Token Index: 802

Text #18

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1658879 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1023947 (The Pile)

Max Activating Token Index: 739