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

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

Neuron 4409 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5478. Min Act: -0.0000

Data Index: 844073 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5277. Min Act: -0.0000

Data Index: 508417 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.5303. Min Act: -0.0000

Data Index: 838502 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1289048 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4625. Min Act: -0.0000

Data Index: 477091 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1092261 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4254. Min Act: -0.0000

Data Index: 481581 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.3802. Min Act: -0.0000

Data Index: 160669 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1121267 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4058. Min Act: -0.0000

Data Index: 342850 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4324. Min Act: -0.0000

Data Index: 932335 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4145. Min Act: -0.0000

Data Index: 401110 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4005. Min Act: -0.0000

Data Index: 663443 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1133239 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.3919. Min Act: -0.0000

Data Index: 893445 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.3865. Min Act: -0.0000

Data Index: 275890 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.3988. Min Act: -0.0000

Data Index: 725080 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1351703 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4038. Min Act: -0.0000

Data Index: 162988 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.5478. Min Range: -0.5478

Max Act: 0.4060. Min Act: -0.0000

Data Index: 587833 (C4 (Web Text))

Max Activating Token Index: 178