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

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

Neuron 3801 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1224739 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2164. Min Act: -0.0001

Data Index: 333032 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2224. Min Act: -0.0000

Data Index: 58773 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2115. Min Act: -0.0000

Data Index: 343504 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1210204 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2144. Min Act: -0.0000

Data Index: 253976 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2072. Min Act: -0.0000

Data Index: 849804 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1215402 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2020. Min Act: -0.0000

Data Index: 977856 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1351043 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1881. Min Act: -0.0001

Data Index: 163783 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1043873 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1901. Min Act: -0.0000

Data Index: 5327 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1763. Min Act: -0.0000

Data Index: 977428 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1047546 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1807. Min Act: -0.0001

Data Index: 83466 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1829. Min Act: -0.0000

Data Index: 671905 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1718. Min Act: -0.0000

Data Index: 346986 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1628. Min Act: -0.0000

Data Index: 990363 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.2343. Min Range: -0.2343

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1197597 (C4 (Web Text))

Max Activating Token Index: 705