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

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

Neuron 2179 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.3009. Min Act: -0.0000

Data Index: 567359 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2228. Min Act: -0.0000

Data Index: 272308 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2428. Min Act: 0.0000

Data Index: 745412 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2256. Min Act: -0.0000

Data Index: 257157 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1214883 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2085. Min Act: -0.0000

Data Index: 732748 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1839. Min Act: -0.0000

Data Index: 472101 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1854. Min Act: -0.0000

Data Index: 210102 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1758. Min Act: -0.0000

Data Index: 593592 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1061654 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1116201 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1067932 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1066096 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1687. Min Act: -0.0000

Data Index: 292838 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1264932 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1676. Min Act: -0.0000

Data Index: 600131 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1666. Min Act: -0.0000

Data Index: 464436 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1602. Min Act: -0.0000

Data Index: 966804 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1773. Min Act: -0.0000

Data Index: 953393 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1548. Min Act: -0.0000

Data Index: 922973 (C4 (Web Text))

Max Activating Token Index: 296