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

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

Neuron 1421 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1281984 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1178914 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2064. Min Act: -0.0001

Data Index: 424441 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1782. Min Act: -0.0001

Data Index: 607078 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1096013 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1744. Min Act: -0.0001

Data Index: 939 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1691. Min Act: -0.0001

Data Index: 95515 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1556. Min Act: -0.0001

Data Index: 610892 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1604. Min Act: -0.0001

Data Index: 222837 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1034247 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1554. Min Act: -0.0001

Data Index: 213494 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1054060 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1371. Min Act: -0.0001

Data Index: 144160 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1374. Min Act: -0.0001

Data Index: 860546 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1477. Min Act: -0.0001

Data Index: 111685 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1366. Min Act: -0.0001

Data Index: 515211 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1544. Min Act: -0.0001

Data Index: 887082 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1336. Min Act: -0.0001

Data Index: 103320 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1053386 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1386. Min Act: -0.0001

Data Index: 107954 (C4 (Web Text))

Max Activating Token Index: 625