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

Dataset: The Pile

Neuron 4192 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4930. Min Act: -0.0000

Data Index: 661437 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1486118 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4969. Min Act: -0.0000

Data Index: 262065 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1948583 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1123070 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1426990 (The Pile)

Max Activating Token Index: 760

Text #6

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4648. Min Act: -0.0000

Data Index: 703130 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4415. Min Act: -0.0000

Data Index: 806059 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4178. Min Act: -0.0000

Data Index: 888283 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1114120 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1278277 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3823. Min Act: -0.0000

Data Index: 776029 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1249711 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4182. Min Act: -0.0000

Data Index: 928599 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1713005 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3979. Min Act: -0.0000

Data Index: 815851 (The Pile)

Max Activating Token Index: 702

Text #16

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3978. Min Act: -0.0000

Data Index: 974599 (The Pile)

Max Activating Token Index: 299

Text #17

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.4268. Min Act: -0.0000

Data Index: 29468 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1719435 (The Pile)

Max Activating Token Index: 988

Text #19

Max Range: 0.4969. Min Range: -0.4969

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1671445 (The Pile)

Max Activating Token Index: 222