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

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

Neuron 4772 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.4101. Min Act: -0.0000

Data Index: 104109 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3584. Min Act: -0.0000

Data Index: 593453 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1190174 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1742. Min Act: -0.0000

Data Index: 720967 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1629. Min Act: -0.0000

Data Index: 877539 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1659. Min Act: -0.0000

Data Index: 852575 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1637. Min Act: -0.0000

Data Index: 761937 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1530. Min Act: -0.0000

Data Index: 842113 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1512. Min Act: -0.0000

Data Index: 447636 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1418. Min Act: -0.0000

Data Index: 781927 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1441. Min Act: -0.0000

Data Index: 49609 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1126687 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1305. Min Act: -0.0000

Data Index: 413353 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1308. Min Act: -0.0000

Data Index: 862747 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1181. Min Act: -0.0000

Data Index: 68418 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1191420 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1267. Min Act: -0.0000

Data Index: 853093 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1296. Min Act: -0.0000

Data Index: 7179 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1230. Min Act: -0.0000

Data Index: 943333 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.1261. Min Act: -0.0000

Data Index: 171336 (C4 (Web Text))

Max Activating Token Index: 589