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

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

Neuron 2701 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: 2.4078. Min Range: -2.4078

Max Act: 2.4078. Min Act: -0.0000

Data Index: 1456088 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.2571. Min Act: -0.0000

Data Index: 455170 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 2.4078. Min Range: -2.4078

Max Act: 2.1446. Min Act: -0.0000

Data Index: 1481958 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.8446. Min Act: -0.0000

Data Index: 344010 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.6935. Min Act: -0.0000

Data Index: 1200958 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.7681. Min Act: -0.0000

Data Index: 740918 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.6547. Min Act: -0.0000

Data Index: 471362 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1301779 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1010942 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1405047 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.5804. Min Act: -0.0000

Data Index: 217389 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.5821. Min Act: -0.0000

Data Index: 1519102 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1471464 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.4474. Min Act: -0.0000

Data Index: 413793 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.4159. Min Act: -0.0000

Data Index: 793459 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1115383 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.5504. Min Act: -0.0000

Data Index: 1491649 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.3199. Min Act: -0.0000

Data Index: 18926 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.4950. Min Act: -0.0000

Data Index: 773725 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 2.4078. Min Range: -2.4078

Max Act: 1.3141. Min Act: -0.0000

Data Index: 618930 (C4 (Web Text))

Max Activating Token Index: 309