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

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

Neuron 2853 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: 2.2705. Min Range: -2.2705

Max Act: 2.2705. Min Act: -0.0000

Data Index: 1629664 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 2.2705. Min Range: -2.2705

Max Act: 2.2127. Min Act: -0.0000

Data Index: 1479192 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 2.2705. Min Range: -2.2705

Max Act: 2.0192. Min Act: -0.0000

Data Index: 1638880 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 2.2705. Min Range: -2.2705

Max Act: 2.0041. Min Act: -0.0000

Data Index: 1530550 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.9632. Min Act: -0.0000

Data Index: 1487913 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.9170. Min Act: -0.0000

Data Index: 1370574 (Python Code)

Max Activating Token Index: 535

Text #6

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.8010. Min Act: -0.0000

Data Index: 1432934 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.9051. Min Act: -0.0000

Data Index: 1450218 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.7688. Min Act: -0.0000

Data Index: 1394290 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.8615. Min Act: -0.0000

Data Index: 1413093 (Python Code)

Max Activating Token Index: 450

Text #10

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.7586. Min Act: -0.0000

Data Index: 1653150 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1397867 (Python Code)

Max Activating Token Index: 692

Text #12

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.7943. Min Act: -0.0000

Data Index: 1417997 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1614042 (Python Code)

Max Activating Token Index: 910

Text #14

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.8579. Min Act: -0.0000

Data Index: 1615647 (Python Code)

Max Activating Token Index: 416

Text #15

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.8593. Min Act: -0.0000

Data Index: 1423800 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1403262 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.6981. Min Act: -0.0000

Data Index: 1601673 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1395899 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 2.2705. Min Range: -2.2705

Max Act: 1.6640. Min Act: -0.0000

Data Index: 1418803 (Python Code)

Max Activating Token Index: 68