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

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

Neuron 3848 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.4231. Min Act: -0.0000

Data Index: 423634 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1339083 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1380909 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3434. Min Act: -0.0000

Data Index: 187365 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3328. Min Act: -0.0000

Data Index: 329562 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2679. Min Act: -0.0000

Data Index: 629366 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3009. Min Act: -0.0000

Data Index: 546581 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2483. Min Act: -0.0000

Data Index: 560308 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2333. Min Act: -0.0000

Data Index: 785513 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2065. Min Act: -0.0000

Data Index: 678462 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1056722 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2533. Min Act: -0.0000

Data Index: 515223 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2643. Min Act: -0.0000

Data Index: 884619 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2022. Min Act: -0.0000

Data Index: 637601 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2049. Min Act: -0.0000

Data Index: 847232 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1459016 (Python Code)

Max Activating Token Index: 174

Text #16

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1336023 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1515266 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1348499 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 1.4666. Min Range: -1.4666

Max Act: 1.1731. Min Act: -0.0000

Data Index: 180847 (C4 (Web Text))

Max Activating Token Index: 503