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

Dataset: The Pile

Neuron 1578 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: 0.5347. Min Range: -0.5347

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1359839 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1538951 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4136. Min Act: -0.0000

Data Index: 747363 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1957070 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4173. Min Act: 0.0000

Data Index: 338986 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1330500 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3927. Min Act: -0.0000

Data Index: 478762 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3744. Min Act: 0.0000

Data Index: 1096372 (The Pile)

Max Activating Token Index: 868

Text #8

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1246376 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1457117 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3341. Min Act: -0.0000

Data Index: 493719 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3623. Min Act: -0.0000

Data Index: 254806 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3460. Min Act: -0.0000

Data Index: 848458 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3343. Min Act: 0.0001

Data Index: 948106 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3332. Min Act: -0.0000

Data Index: 543352 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3432. Min Act: -0.0000

Data Index: 675243 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.2961. Min Act: -0.0000

Data Index: 787750 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3417. Min Act: -0.0000

Data Index: 852625 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3450. Min Act: 0.0000

Data Index: 209959 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.5347. Min Range: -0.5347

Max Act: 0.3304. Min Act: -0.0000

Data Index: 242694 (The Pile)

Max Activating Token Index: 89