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

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

Neuron 4682 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.1372. Min Act: -0.0000

Data Index: 632211 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.1471. Min Act: -0.0000

Data Index: 866070 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0784. Min Act: -0.0000

Data Index: 989198 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0077. Min Act: -0.0000

Data Index: 746798 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0503. Min Act: -0.0000

Data Index: 964758 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0146. Min Act: -0.0000

Data Index: 846072 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0091. Min Act: -0.0000

Data Index: 442121 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1282978 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9217. Min Act: -0.0000

Data Index: 217773 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9809. Min Act: -0.0000

Data Index: 970236 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9749. Min Act: -0.0000

Data Index: 963491 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9188. Min Act: -0.0000

Data Index: 182779 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1154076 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1221425 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8965. Min Act: -0.0000

Data Index: 184031 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1097856 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1152554 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8103. Min Act: -0.0000

Data Index: 483068 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8748. Min Act: -0.0000

Data Index: 368847 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8136. Min Act: -0.0000

Data Index: 544079 (C4 (Web Text))

Max Activating Token Index: 589