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

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

Neuron 556 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: 5.4361. Min Range: -5.4361

Max Act: 5.4361. Min Act: -0.0000

Data Index: 627356 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.3900. Min Act: -0.0000

Data Index: 1100498 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.4170. Min Act: -0.0000

Data Index: 721382 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.1187. Min Act: -0.0000

Data Index: 1398381 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.4508. Min Act: -0.0000

Data Index: 1189107 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.9592. Min Act: -0.0000

Data Index: 976750 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.2699. Min Act: -0.0000

Data Index: 492603 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.1240. Min Act: -0.0000

Data Index: 1274042 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.9258. Min Act: -0.0000

Data Index: 949041 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.0529. Min Act: -0.0000

Data Index: 1170170 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 5.4361. Min Range: -5.4361

Max Act: 4.0477. Min Act: -0.0000

Data Index: 936318 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.8430. Min Act: -0.0000

Data Index: 70327 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.7574. Min Act: -0.0000

Data Index: 805202 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.7071. Min Act: -0.0000

Data Index: 1308481 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.4364. Min Act: -0.0000

Data Index: 462016 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 5.4361. Min Range: -5.4361

Max Act: 2.9692. Min Act: -0.0000

Data Index: 492923 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.3034. Min Act: -0.0000

Data Index: 661405 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.4092. Min Act: -0.0000

Data Index: 80280 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.2620. Min Act: -0.0000

Data Index: 608541 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 5.4361. Min Range: -5.4361

Max Act: 3.1057. Min Act: -0.0000

Data Index: 114543 (C4 (Web Text))

Max Activating Token Index: 961