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

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

Neuron 2629 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.1607. Min Act: -0.0000

Data Index: 99104 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0604. Min Act: -0.0000

Data Index: 259433 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9858. Min Act: -0.0000

Data Index: 580053 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1091610 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.1059. Min Act: -0.0000

Data Index: 922191 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0241. Min Act: -0.0000

Data Index: 559796 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0059. Min Act: -0.0000

Data Index: 306370 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9203. Min Act: -0.0000

Data Index: 14414 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9967. Min Act: -0.0000

Data Index: 716451 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0113. Min Act: -0.0000

Data Index: 159897 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8952. Min Act: -0.0000

Data Index: 150101 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9196. Min Act: -0.0000

Data Index: 122473 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9258. Min Act: -0.0000

Data Index: 208081 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8795. Min Act: -0.0000

Data Index: 11869 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9408. Min Act: -0.0000

Data Index: 346097 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1262115 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8505. Min Act: -0.0000

Data Index: 16749 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1012390 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1384454 (Python Code)

Max Activating Token Index: 916

Text #19

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8271. Min Act: -0.0000

Data Index: 407101 (C4 (Web Text))

Max Activating Token Index: 8