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

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

Neuron 110 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.9064. Min Act: -0.0000

Data Index: 686867 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8019. Min Act: -0.0000

Data Index: 545313 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7853. Min Act: -0.0000

Data Index: 276092 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7468. Min Act: -0.0000

Data Index: 663447 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6926. Min Act: -0.0000

Data Index: 583419 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7278. Min Act: -0.0000

Data Index: 674084 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6975. Min Act: -0.0000

Data Index: 106425 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6961. Min Act: -0.0000

Data Index: 626115 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6659. Min Act: -0.0000

Data Index: 42923 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7079. Min Act: -0.0000

Data Index: 734695 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7266. Min Act: -0.0000

Data Index: 385001 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1199239 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6049. Min Act: -0.0000

Data Index: 229321 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1461332 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1014457 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6130. Min Act: -0.0000

Data Index: 352490 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1118307 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5952. Min Act: -0.0000

Data Index: 736 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6022. Min Act: -0.0000

Data Index: 921632 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1307733 (C4 (Web Text))

Max Activating Token Index: 637