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

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

Neuron 4015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3999. Min Act: -0.0001

Data Index: 530640 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.4982. Min Act: -0.0001

Data Index: 1154689 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.5681. Min Act: -0.0001

Data Index: 273757 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3740. Min Act: -0.0001

Data Index: 524629 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3849. Min Act: -0.0001

Data Index: 38652 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3564. Min Act: -0.0001

Data Index: 1565055 (Python Code)

Max Activating Token Index: 360

Text #6

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.4065. Min Act: -0.0001

Data Index: 1152032 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3562. Min Act: -0.0001

Data Index: 69815 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3769. Min Act: -0.0001

Data Index: 302409 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3129. Min Act: -0.0001

Data Index: 393293 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2128. Min Act: -0.0001

Data Index: 170012 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3361. Min Act: -0.0001

Data Index: 72906 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3044. Min Act: -0.0001

Data Index: 967023 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.3190. Min Act: -0.0001

Data Index: 649302 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1777. Min Act: -0.0001

Data Index: 629023 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2772. Min Act: -0.0001

Data Index: 832107 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1734. Min Act: -0.0001

Data Index: 330849 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.1741. Min Act: -0.0001

Data Index: 102998 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2120. Min Act: -0.0001

Data Index: 361298 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.5681. Min Range: -1.5681

Max Act: 1.2418. Min Act: -0.0001

Data Index: 480199 (C4 (Web Text))

Max Activating Token Index: 116