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

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

Neuron 2603 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.7781. Min Act: -0.0001

Data Index: 29816 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.6045. Min Act: -0.0000

Data Index: 759152 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.6101. Min Act: -0.0000

Data Index: 823895 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.5969. Min Act: -0.0000

Data Index: 384073 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.5506. Min Act: -0.0001

Data Index: 366573 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.2136. Min Act: -0.0000

Data Index: 1117119 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.3187. Min Act: -0.0000

Data Index: 842826 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.2418. Min Act: -0.0001

Data Index: 944331 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 2.7781. Min Range: -2.7781

Max Act: 2.0653. Min Act: -0.0000

Data Index: 1326688 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.9946. Min Act: -0.0000

Data Index: 998736 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.8734. Min Act: -0.0001

Data Index: 566369 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.6278. Min Act: -0.0000

Data Index: 538095 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.5994. Min Act: -0.0001

Data Index: 978835 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.5448. Min Act: -0.0001

Data Index: 1146679 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.5827. Min Act: -0.0000

Data Index: 976229 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.5443. Min Act: -0.0000

Data Index: 239053 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.5045. Min Act: -0.0000

Data Index: 763779 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.4957. Min Act: -0.0001

Data Index: 692366 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.5746. Min Act: -0.0001

Data Index: 414918 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.7781. Min Range: -2.7781

Max Act: 1.6171. Min Act: -0.0000

Data Index: 659768 (C4 (Web Text))

Max Activating Token Index: 157