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

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

Neuron 5073 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: 3.0313. Min Range: -3.0313

Max Act: 3.0313. Min Act: -0.0000

Data Index: 194774 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.2053. Min Act: -0.0000

Data Index: 359849 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.9389. Min Act: -0.0000

Data Index: 156115 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.9725. Min Act: -0.0000

Data Index: 756192 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.0746. Min Act: -0.0000

Data Index: 508132 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.9498. Min Act: -0.0000

Data Index: 672229 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.8060. Min Act: -0.0000

Data Index: 47944 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.9041. Min Act: -0.0000

Data Index: 11596 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.8528. Min Act: -0.0000

Data Index: 478375 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.9406. Min Act: -0.0000

Data Index: 1290953 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.8389. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.8349. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.7101. Min Act: -0.0000

Data Index: 218924 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.9060. Min Act: -0.0000

Data Index: 210687 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.8041. Min Act: -0.0000

Data Index: 95662 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.7950. Min Act: -0.0000

Data Index: 947654 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.8551. Min Act: -0.0000

Data Index: 1130914 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.5683. Min Act: -0.0000

Data Index: 533952 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.7313. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 3.0313. Min Range: -3.0313

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1645147 (Python Code)

Max Activating Token Index: 1007