Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2092. Min Act: -0.0001

Data Index: 896373 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1215073 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2273. Min Act: -0.0001

Data Index: 1206317 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1056355 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1906. Min Act: -0.0001

Data Index: 613531 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1237602 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1986. Min Act: -0.0000

Data Index: 382219 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1961. Min Act: -0.0001

Data Index: 635399 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2012. Min Act: -0.0001

Data Index: 417054 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1874. Min Act: -0.0001

Data Index: 190565 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1971. Min Act: -0.0001

Data Index: 254083 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1934. Min Act: -0.0001

Data Index: 156373 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1660. Min Act: -0.0001

Data Index: 612647 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1964. Min Act: -0.0001

Data Index: 645448 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.2077. Min Act: -0.0001

Data Index: 40341 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1929. Min Act: -0.0001

Data Index: 807106 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1910. Min Act: -0.0001

Data Index: 432326 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1837. Min Act: -0.0001

Data Index: 669153 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1900. Min Act: -0.0001

Data Index: 564644 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.2273. Min Range: -0.2273

Max Act: 0.1644. Min Act: -0.0001

Data Index: 79619 (C4 (Web Text))

Max Activating Token Index: 910