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

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

Neuron 5052 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1643741 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1101812 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1379574 (Python Code)

Max Activating Token Index: 946

Text #3

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1582894 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1496975 (Python Code)

Max Activating Token Index: 861

Text #5

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1480728 (Python Code)

Max Activating Token Index: 590

Text #6

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5251. Min Act: -0.0000

Data Index: 285523 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1616273 (Python Code)

Max Activating Token Index: 199

Text #8

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1390366 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1000240 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1631780 (Python Code)

Max Activating Token Index: 558

Text #11

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1560855 (Python Code)

Max Activating Token Index: 853

Text #12

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1495916 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1125137 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5080. Min Act: -0.0000

Data Index: 295394 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4546. Min Act: -0.0000

Data Index: 433011 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4808. Min Act: -0.0000

Data Index: 16145 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4962. Min Act: -0.0000

Data Index: 299830 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1388244 (Python Code)

Max Activating Token Index: 102

Text #19

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1487151 (Python Code)

Max Activating Token Index: 27