Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 424 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.8169. Min Act: -0.0000

Data Index: 96518 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1164850 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1348869 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1172309 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6157. Min Act: 0.0000

Data Index: 1016390 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6289. Min Act: -0.0001

Data Index: 587946 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6045. Min Act: -0.0001

Data Index: 1414206 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6336. Min Act: -0.0001

Data Index: 1478704 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1208784 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1110109 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.5520. Min Act: -0.0000

Data Index: 536555 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.5547. Min Act: -0.0001

Data Index: 452429 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.5263. Min Act: -0.0000

Data Index: 230508 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.5245. Min Act: -0.0000

Data Index: 525409 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1221425 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1226870 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.4737. Min Act: -0.0000

Data Index: 485862 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.4798. Min Act: -0.0001

Data Index: 1631152 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.4630. Min Act: -0.0001

Data Index: 979914 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.4490. Min Act: -0.0000

Data Index: 531358 (C4 (Web Text))

Max Activating Token Index: 920