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

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

Neuron 655 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: 1.4158. Min Range: -1.4158

Max Act: 1.3973. Min Act: -0.0000

Data Index: 81784 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.3259. Min Act: -0.0000

Data Index: 403159 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.3812. Min Act: -0.0000

Data Index: 364289 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1079197 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2185. Min Act: -0.0000

Data Index: 1022932 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1050966 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.2501. Min Act: -0.0000

Data Index: 330252 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1562. Min Act: -0.0000

Data Index: 17765 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1800. Min Act: -0.0000

Data Index: 381858 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.1034. Min Act: -0.0000

Data Index: 472085 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.4158. Min Range: -1.4158

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1026917 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1153919 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.9147. Min Act: -0.0000

Data Index: 242344 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.9758. Min Act: -0.0000

Data Index: 101804 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.9015. Min Act: -0.0000

Data Index: 410751 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.9047. Min Act: -0.0000

Data Index: 529710 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.9284. Min Act: -0.0000

Data Index: 144719 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1083519 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.8547. Min Act: -0.0000

Data Index: 935093 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 1.4158. Min Range: -1.4158

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1078217 (C4 (Web Text))

Max Activating Token Index: 785