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

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

Neuron 618 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: 0.8002. Min Range: -0.8002

Max Act: 0.8002. Min Act: -0.0000

Data Index: 262061 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7694. Min Act: -0.0000

Data Index: 615953 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7036. Min Act: -0.0000

Data Index: 418229 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7101. Min Act: -0.0000

Data Index: 55376 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1079316 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7079. Min Act: -0.0000

Data Index: 618943 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6836. Min Act: -0.0000

Data Index: 443072 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6553. Min Act: -0.0000

Data Index: 380047 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1157711 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6468. Min Act: -0.0000

Data Index: 980691 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6058. Min Act: -0.0000

Data Index: 653351 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1201803 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.6113. Min Act: -0.0000

Data Index: 926412 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5791. Min Act: -0.0000

Data Index: 650742 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5458. Min Act: -0.0000

Data Index: 972292 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5758. Min Act: -0.0000

Data Index: 22321 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5983. Min Act: -0.0000

Data Index: 134442 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5799. Min Act: -0.0000

Data Index: 433596 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5344. Min Act: -0.0000

Data Index: 483570 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.8002. Min Range: -0.8002

Max Act: 0.5653. Min Act: -0.0000

Data Index: 640875 (C4 (Web Text))

Max Activating Token Index: 251