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

Dataset: The Pile

Neuron 181 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1212623 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1208448 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1391179 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1440475 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.3668. Min Act: -0.0000

Data Index: 637377 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.3509. Min Act: -0.0000

Data Index: 164176 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1824781 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1051087 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1332319 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1709102 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1281669 (The Pile)

Max Activating Token Index: 958

Text #11

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1932108 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.1649. Min Act: -0.0000

Data Index: 995403 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.1220. Min Act: -0.0000

Data Index: 38380 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.1265. Min Act: -0.0000

Data Index: 661986 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1887515 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1159554 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1763909 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.0857. Min Act: -0.0000

Data Index: 230562 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1292727 (The Pile)

Max Activating Token Index: 137