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

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

Neuron 5079 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1205030 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1167. Min Act: -0.0000

Data Index: 713246 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1135. Min Act: -0.0000

Data Index: 271518 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1069. Min Act: -0.0000

Data Index: 81873 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1542692 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1142. Min Act: -0.0000

Data Index: 425478 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1037. Min Act: -0.0000

Data Index: 97243 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1131. Min Act: -0.0000

Data Index: 143398 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1053. Min Act: -0.0000

Data Index: 209185 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1478386 (Python Code)

Max Activating Token Index: 186

Text #10

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1154188 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1541081 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1590203 (Python Code)

Max Activating Token Index: 471

Text #13

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1034. Min Act: -0.0000

Data Index: 958046 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0984. Min Act: -0.0000

Data Index: 844104 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0979. Min Act: -0.0000

Data Index: 945105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0976. Min Act: -0.0000

Data Index: 723292 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1306076 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.0946. Min Act: -0.0000

Data Index: 663867 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.1317. Min Range: -0.1317

Max Act: 0.1025. Min Act: -0.0000

Data Index: 530214 (C4 (Web Text))

Max Activating Token Index: 445