Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1876 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1207. Min Range: -1.1207

Max Act: 1.1207. Min Act: -0.0001

Data Index: 1361460 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1582892 (Python Code)

Max Activating Token Index: 474

Text #2

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.9866. Min Act: -0.0000

Data Index: 550028 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.9904. Min Act: -0.0001

Data Index: 86308 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.9987. Min Act: -0.0001

Data Index: 307976 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1599602 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1201757 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.9035. Min Act: -0.0001

Data Index: 1472568 (Python Code)

Max Activating Token Index: 680

Text #8

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1461403 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8530. Min Act: -0.0001

Data Index: 486579 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1197841 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8747. Min Act: -0.0001

Data Index: 1470823 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1562345 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1507228 (Python Code)

Max Activating Token Index: 853

Text #14

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8301. Min Act: -0.0000

Data Index: 100148 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1257404 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1557646 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1150224 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8296. Min Act: -0.0000

Data Index: 425308 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.1207. Min Range: -1.1207

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1607127 (Python Code)

Max Activating Token Index: 815