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

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

Neuron 591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7611. Min Range: -2.7611

Max Act: 2.7611. Min Act: -0.0000

Data Index: 135865 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 2.7611. Min Range: -2.7611

Max Act: 2.1361. Min Act: -0.0000

Data Index: 999868 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 2.7611. Min Range: -2.7611

Max Act: 2.0644. Min Act: -0.0000

Data Index: 922750 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.9080. Min Act: -0.0000

Data Index: 1335317 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.8276. Min Act: -0.0000

Data Index: 48444 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.9233. Min Act: -0.0000

Data Index: 1032563 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.7023. Min Act: -0.0000

Data Index: 317807 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.6950. Min Act: -0.0000

Data Index: 1185591 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.6295. Min Act: -0.0000

Data Index: 867525 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1123009 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.5224. Min Act: -0.0000

Data Index: 304990 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.6879. Min Act: -0.0000

Data Index: 1029075 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.5907. Min Act: -0.0000

Data Index: 473200 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.5919. Min Act: -0.0000

Data Index: 589176 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.5930. Min Act: -0.0000

Data Index: 671149 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.5498. Min Act: -0.0000

Data Index: 165213 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.5385. Min Act: -0.0000

Data Index: 511859 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.2571. Min Act: -0.0000

Data Index: 158399 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.4110. Min Act: -0.0000

Data Index: 1265776 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 2.7611. Min Range: -2.7611

Max Act: 1.4129. Min Act: -0.0000

Data Index: 68492 (C4 (Web Text))

Max Activating Token Index: 507