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

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

Neuron 2872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3713. Min Act: -0.0001

Data Index: 756617 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2895. Min Act: -0.0000

Data Index: 363933 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2518. Min Act: -0.0001

Data Index: 1119032 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3647. Min Act: -0.0000

Data Index: 433930 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2401. Min Act: -0.0001

Data Index: 750853 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1781. Min Act: -0.0001

Data Index: 1171864 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1349. Min Act: -0.0001

Data Index: 509103 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1244. Min Act: -0.0001

Data Index: 1190300 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0870. Min Act: -0.0001

Data Index: 517615 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1766. Min Act: -0.0000

Data Index: 434385 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1093. Min Act: -0.0001

Data Index: 372834 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2515. Min Act: -0.0000

Data Index: 773153 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0713. Min Act: -0.0000

Data Index: 167958 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1444. Min Act: -0.0001

Data Index: 49870 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0770. Min Act: 0.0000

Data Index: 345119 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0522. Min Act: -0.0001

Data Index: 139157 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2077. Min Act: -0.0001

Data Index: 1025458 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0970. Min Act: -0.0001

Data Index: 266433 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9165. Min Act: -0.0001

Data Index: 991983 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1981. Min Act: -0.0001

Data Index: 422732 (C4 (Web Text))

Max Activating Token Index: 238