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

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

Neuron 2401 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2619. Min Act: -0.0001

Data Index: 35926 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1115975 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2662. Min Act: -0.0001

Data Index: 238348 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2224. Min Act: -0.0002

Data Index: 1309928 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2179. Min Act: -0.0002

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2199. Min Act: -0.0002

Data Index: 896671 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1064914 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2062. Min Act: -0.0002

Data Index: 272506 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2258. Min Act: -0.0001

Data Index: 1211775 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2277. Min Act: -0.0002

Data Index: 904396 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2099. Min Act: -0.0001

Data Index: 59855 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2107. Min Act: -0.0001

Data Index: 787591 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1066032 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2131. Min Act: -0.0002

Data Index: 242167 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2130. Min Act: -0.0001

Data Index: 264961 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2219. Min Act: -0.0002

Data Index: 1009538 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2199. Min Act: -0.0002

Data Index: 450921 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2160. Min Act: -0.0001

Data Index: 966495 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2007. Min Act: -0.0001

Data Index: 626429 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2036. Min Act: -0.0002

Data Index: 110128 (C4 (Web Text))

Max Activating Token Index: 845