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

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

Neuron 247 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1583142 (Python Code)

Max Activating Token Index: 278

Text #1

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7142. Min Act: -0.0000

Data Index: 264876 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1222628 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6471. Min Act: -0.0000

Data Index: 378461 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1112338 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1018446 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1286311 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6493. Min Act: -0.0000

Data Index: 262220 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6575. Min Act: -0.0000

Data Index: 480251 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1366154 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1556637 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5927. Min Act: -0.0000

Data Index: 686685 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1586910 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.6094. Min Act: -0.0000

Data Index: 325832 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1369883 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1043282 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1419930 (Python Code)

Max Activating Token Index: 936

Text #17

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1620179 (Python Code)

Max Activating Token Index: 933

Text #18

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5918. Min Act: -0.0000

Data Index: 894273 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.7475. Min Range: -0.7475

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1455240 (Python Code)

Max Activating Token Index: 590