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

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

Neuron 1734 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: 0.5609. Min Range: -0.5609

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1291027 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.5011. Min Act: -0.0001

Data Index: 1178113 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4330. Min Act: -0.0001

Data Index: 208353 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1157734 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4575. Min Act: -0.0001

Data Index: 529098 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4503. Min Act: -0.0001

Data Index: 219255 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4131. Min Act: -0.0001

Data Index: 477015 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4005. Min Act: -0.0001

Data Index: 541251 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4285. Min Act: -0.0001

Data Index: 632434 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4351. Min Act: -0.0001

Data Index: 205972 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3823. Min Act: -0.0001

Data Index: 162634 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1035955 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4181. Min Act: -0.0001

Data Index: 1009099 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3716. Min Act: -0.0001

Data Index: 1310785 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3840. Min Act: -0.0001

Data Index: 549901 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3838. Min Act: -0.0001

Data Index: 811306 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3563. Min Act: -0.0001

Data Index: 33784 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3560. Min Act: -0.0001

Data Index: 989269 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3934. Min Act: -0.0001

Data Index: 663339 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1067188 (C4 (Web Text))

Max Activating Token Index: 461