Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3181 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6872. Min Act: 0.0000

Data Index: 120125 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.5197. Min Act: 0.0000

Data Index: 32948 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4565. Min Act: -0.0000

Data Index: 905044 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1161587 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3827. Min Act: -0.0000

Data Index: 670159 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3903. Min Act: -0.0000

Data Index: 503959 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1125880 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3822. Min Act: -0.0000

Data Index: 290671 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3775. Min Act: 0.0000

Data Index: 1284477 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3675. Min Act: -0.0000

Data Index: 785916 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3650. Min Act: -0.0000

Data Index: 443630 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3696. Min Act: -0.0000

Data Index: 387667 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1089279 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3518. Min Act: 0.0000

Data Index: 1335 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3616. Min Act: -0.0000

Data Index: 881602 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3717. Min Act: -0.0000

Data Index: 628362 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3735. Min Act: -0.0000

Data Index: 360065 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1275919 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3540. Min Act: -0.0000

Data Index: 124789 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1041172 (C4 (Web Text))

Max Activating Token Index: 484