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

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

Neuron 2056 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1539008 (Python Code)

Max Activating Token Index: 804

Text #1

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.4532. Min Act: -0.0001

Data Index: 1591576 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1469776 (Python Code)

Max Activating Token Index: 401

Text #3

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1488537 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3948. Min Act: -0.0001

Data Index: 1434917 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1624632 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1447709 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1593880 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1610920 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1540319 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1550309 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2505. Min Act: -0.0001

Data Index: 925947 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1485544 (Python Code)

Max Activating Token Index: 681

Text #13

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2390. Min Act: -0.0001

Data Index: 60112 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2337. Min Act: -0.0001

Data Index: 1469281 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1386889 (Python Code)

Max Activating Token Index: 741

Text #16

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1381925 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1037187 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1588136 (Python Code)

Max Activating Token Index: 943

Text #19

Max Range: 0.4544. Min Range: -0.4544

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1356753 (C4 (Web Text))

Max Activating Token Index: 725