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

Dataset: The Pile

Neuron 3985 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: 1.0879. Min Range: -1.0879

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1077630 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 1.0879. Min Range: -1.0879

Max Act: 1.0879. Min Act: -0.0000

Data Index: 151083 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.0879. Min Range: -1.0879

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1335419 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1173692 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1172913 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8806. Min Act: -0.0000

Data Index: 711464 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1080845 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8729. Min Act: -0.0000

Data Index: 983302 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.9010. Min Act: -0.0000

Data Index: 327144 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1018786 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1293019 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8545. Min Act: -0.0000

Data Index: 958901 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8600. Min Act: 0.0000

Data Index: 1588895 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8498. Min Act: -0.0000

Data Index: 859254 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1291652 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8471. Min Act: -0.0000

Data Index: 554521 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8426. Min Act: -0.0000

Data Index: 114975 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8451. Min Act: -0.0000

Data Index: 764433 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1979562 (The Pile)

Max Activating Token Index: 324

Text #19

Max Range: 1.0879. Min Range: -1.0879

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1162032 (The Pile)

Max Activating Token Index: 532