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

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

Neuron 5031 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.5324. Min Act: -0.0000

Data Index: 989177 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.3462. Min Act: -0.0000

Data Index: 1311490 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1079750 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.3047. Min Act: -0.0000

Data Index: 1391342 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.3000. Min Act: -0.0000

Data Index: 1101227 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.4178. Min Act: -0.0000

Data Index: 1249998 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1001403 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.2066. Min Act: -0.0000

Data Index: 1510569 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.4008. Min Act: -0.0000

Data Index: 332918 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1601. Min Act: -0.0000

Data Index: 1037278 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.2201. Min Act: -0.0000

Data Index: 1400204 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.2263. Min Act: -0.0000

Data Index: 1622235 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.3325. Min Act: -0.0000

Data Index: 1631941 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.0841. Min Act: -0.0000

Data Index: 1497128 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1902. Min Act: -0.0000

Data Index: 1291992 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1813. Min Act: -0.0000

Data Index: 665692 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.0494. Min Act: -0.0000

Data Index: 1023029 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1401. Min Act: -0.0000

Data Index: 1572973 (Python Code)

Max Activating Token Index: 163

Text #18

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1193. Min Act: -0.0000

Data Index: 1259924 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 2.5324. Min Range: -2.5324

Max Act: 2.1787. Min Act: -0.0000

Data Index: 1302863 (C4 (Web Text))

Max Activating Token Index: 909