Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7862. Min Act: -0.0001

Data Index: 850244 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7217. Min Act: -0.0001

Data Index: 694946 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7884. Min Act: -0.0001

Data Index: 712475 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7379. Min Act: -0.0001

Data Index: 69790 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6859. Min Act: -0.0001

Data Index: 361273 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6945. Min Act: -0.0001

Data Index: 1316202 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5782. Min Act: -0.0001

Data Index: 1020577 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6327. Min Act: -0.0001

Data Index: 60504 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6399. Min Act: -0.0001

Data Index: 944321 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6577. Min Act: -0.0001

Data Index: 242073 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6643. Min Act: -0.0001

Data Index: 333989 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6138. Min Act: -0.0001

Data Index: 1339021 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6644. Min Act: -0.0001

Data Index: 813419 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6413. Min Act: -0.0001

Data Index: 1307070 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5846. Min Act: -0.0001

Data Index: 173021 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6835. Min Act: -0.0001

Data Index: 813591 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5694. Min Act: -0.0001

Data Index: 1170454 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1183647 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6011. Min Act: -0.0001

Data Index: 1169578 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5242. Min Act: -0.0001

Data Index: 15017 (C4 (Web Text))

Max Activating Token Index: 304