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

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

Neuron 803 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: 0.3380. Min Range: -0.3380

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1120653 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2495. Min Act: -0.0000

Data Index: 136901 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2261. Min Act: -0.0000

Data Index: 836901 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2130. Min Act: -0.0000

Data Index: 343866 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2192. Min Act: -0.0000

Data Index: 42383 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2070. Min Act: -0.0000

Data Index: 211293 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2139. Min Act: -0.0000

Data Index: 505213 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2051. Min Act: -0.0000

Data Index: 531807 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2162. Min Act: -0.0000

Data Index: 215971 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1970. Min Act: -0.0000

Data Index: 225742 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2036. Min Act: -0.0000

Data Index: 227870 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2141. Min Act: -0.0000

Data Index: 294446 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1865. Min Act: -0.0000

Data Index: 479458 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1934. Min Act: -0.0000

Data Index: 33683 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2001. Min Act: -0.0000

Data Index: 602148 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1924. Min Act: -0.0000

Data Index: 84823 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1283621 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1910. Min Act: -0.0000

Data Index: 37630 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1956. Min Act: -0.0000

Data Index: 250145 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.1964. Min Act: -0.0000

Data Index: 951458 (C4 (Web Text))

Max Activating Token Index: 150