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

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

Neuron 448 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2587. Min Act: -0.0002

Data Index: 784090 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2403. Min Act: -0.0002

Data Index: 393771 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2333. Min Act: -0.0002

Data Index: 588563 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2459. Min Act: -0.0002

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2427. Min Act: -0.0002

Data Index: 864063 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2138. Min Act: -0.0002

Data Index: 1294600 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2260. Min Act: -0.0002

Data Index: 109640 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2064. Min Act: -0.0002

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2081. Min Act: -0.0002

Data Index: 605512 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2149. Min Act: -0.0002

Data Index: 1155700 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2057. Min Act: -0.0002

Data Index: 332733 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2051. Min Act: -0.0002

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2281. Min Act: -0.0001

Data Index: 1354972 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2070. Min Act: -0.0002

Data Index: 66920 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2130. Min Act: -0.0002

Data Index: 286288 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2169. Min Act: -0.0002

Data Index: 452784 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1937. Min Act: -0.0002

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2158. Min Act: -0.0002

Data Index: 566966 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2121. Min Act: -0.0002

Data Index: 776851 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2128. Min Act: -0.0002

Data Index: 263119 (C4 (Web Text))

Max Activating Token Index: 427