Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4853 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1577310 (Python Code)

Max Activating Token Index: 721

Text #2

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2831. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2651. Min Act: -0.0000

Data Index: 284788 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2370. Min Act: -0.0000

Data Index: 433840 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1061972 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2520. Min Act: 0.0000

Data Index: 1650724 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2202. Min Act: -0.0000

Data Index: 384679 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1308668 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2309. Min Act: -0.0000

Data Index: 46050 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2422. Min Act: 0.0000

Data Index: 1581266 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1425617 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1160329 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2253. Min Act: -0.0000

Data Index: 343588 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2356. Min Act: -0.0000

Data Index: 377090 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.1835. Min Act: -0.0000

Data Index: 96956 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1235730 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.1935. Min Act: -0.0000

Data Index: 600516 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2081. Min Act: -0.0000

Data Index: 940446 (C4 (Web Text))

Max Activating Token Index: 733