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

Dataset: The Pile

Neuron 2846 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.9841. Min Act: -0.0000

Data Index: 1571910 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7538. Min Act: -0.0000

Data Index: 856927 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.9184. Min Act: -0.0000

Data Index: 822811 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7396. Min Act: -0.0000

Data Index: 295343 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.4673. Min Act: -0.0000

Data Index: 1115858 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.5997. Min Act: -0.0000

Data Index: 422961 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.5107. Min Act: -0.0000

Data Index: 1293772 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.4808. Min Act: -0.0000

Data Index: 928477 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.3372. Min Act: -0.0000

Data Index: 167468 (The Pile)

Max Activating Token Index: 948

Text #9

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.4540. Min Act: -0.0000

Data Index: 1509752 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.3020. Min Act: -0.0000

Data Index: 537869 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.2621. Min Act: -0.0000

Data Index: 1248214 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.4001. Min Act: -0.0000

Data Index: 1263809 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.3644. Min Act: -0.0000

Data Index: 1127186 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.3549. Min Act: -0.0000

Data Index: 1145422 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.4905. Min Act: -0.0000

Data Index: 897776 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.3392. Min Act: -0.0000

Data Index: 858075 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.3337. Min Act: -0.0000

Data Index: 1649469 (The Pile)

Max Activating Token Index: 770

Text #18

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.2956. Min Act: -0.0000

Data Index: 1379381 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.1668. Min Act: -0.0000

Data Index: 729840 (The Pile)

Max Activating Token Index: 279