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

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

Neuron 3618 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7385. Min Act: -0.0002

Data Index: 1003445 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.8268. Min Act: -0.0002

Data Index: 467123 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6866. Min Act: -0.0002

Data Index: 1044535 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6700. Min Act: -0.0002

Data Index: 169011 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7093. Min Act: -0.0002

Data Index: 38432 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6935. Min Act: -0.0002

Data Index: 418406 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6740. Min Act: -0.0002

Data Index: 531737 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7157. Min Act: -0.0002

Data Index: 1229001 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7168. Min Act: -0.0002

Data Index: 1036887 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7342. Min Act: -0.0002

Data Index: 703970 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7291. Min Act: -0.0002

Data Index: 572846 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.5890. Min Act: -0.0002

Data Index: 1196647 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6789. Min Act: -0.0002

Data Index: 718403 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6127. Min Act: -0.0002

Data Index: 397325 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6780. Min Act: -0.0002

Data Index: 112965 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6598. Min Act: -0.0002

Data Index: 199351 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.7001. Min Act: -0.0002

Data Index: 452507 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.5969. Min Act: -0.0002

Data Index: 711021 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.5961. Min Act: -0.0002

Data Index: 814409 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.8268. Min Range: -0.8268

Max Act: 0.6336. Min Act: -0.0002

Data Index: 1175897 (C4 (Web Text))

Max Activating Token Index: 88