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

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

Neuron 4644 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: 0.1886. Min Range: -0.1886

Max Act: 0.1886. Min Act: 0.0000

Data Index: 856405 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1616. Min Act: 0.0000

Data Index: 1164793 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1595. Min Act: -0.0000

Data Index: 170228 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1181971 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1465. Min Act: 0.0000

Data Index: 541805 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1443. Min Act: 0.0000

Data Index: 1127202 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1331692 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1472. Min Act: -0.0000

Data Index: 677500 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1466. Min Act: -0.0000

Data Index: 355354 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1423. Min Act: 0.0000

Data Index: 1144236 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1414. Min Act: -0.0000

Data Index: 969495 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1404. Min Act: -0.0000

Data Index: 468642 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1428. Min Act: 0.0000

Data Index: 783885 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1022178 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1191. Min Act: -0.0000

Data Index: 225561 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1285. Min Act: -0.0000

Data Index: 556754 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1332. Min Act: -0.0000

Data Index: 89118 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1323. Min Act: -0.0000

Data Index: 984850 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1308. Min Act: -0.0000

Data Index: 831044 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1200. Min Act: -0.0000

Data Index: 778969 (C4 (Web Text))

Max Activating Token Index: 1003