Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5856 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.6163. Min Act: -0.0000

Data Index: 621285 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 4.6163. Min Range: -4.6163

Max Act: 4.1709. Min Act: -0.0000

Data Index: 1010376 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.8291. Min Act: -0.0000

Data Index: 346983 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.8023. Min Act: -0.0000

Data Index: 1112365 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.2699. Min Act: -0.0000

Data Index: 268802 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.2594. Min Act: -0.0000

Data Index: 790076 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.7393. Min Act: -0.0000

Data Index: 209448 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.4924. Min Act: -0.0000

Data Index: 1081253 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.3230. Min Act: -0.0000

Data Index: 1195475 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.1166. Min Act: -0.0000

Data Index: 48147 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.2201. Min Act: -0.0000

Data Index: 189096 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.1966. Min Act: -0.0000

Data Index: 1331171 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.2518. Min Act: -0.0000

Data Index: 104545 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.0344. Min Act: -0.0000

Data Index: 265774 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.0172. Min Act: -0.0000

Data Index: 106257 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 4.6163. Min Range: -4.6163

Max Act: 3.1751. Min Act: -0.0000

Data Index: 1321894 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 4.6163. Min Range: -4.6163

Max Act: 2.6864. Min Act: -0.0000

Data Index: 1115725 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 4.6163. Min Range: -4.6163

Max Act: 2.9729. Min Act: -0.0000

Data Index: 227570 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 4.6163. Min Range: -4.6163

Max Act: 2.9361. Min Act: -0.0000

Data Index: 131523 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 4.6163. Min Range: -4.6163

Max Act: 2.9286. Min Act: -0.0000

Data Index: 676083 (C4 (Web Text))

Max Activating Token Index: 513