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

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

Neuron 3935 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: 1.2985. Min Range: -1.2985

Max Act: 1.2985. Min Act: -0.0001

Data Index: 1236488 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0786. Min Act: -0.0001

Data Index: 25865 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0765. Min Act: -0.0001

Data Index: 223336 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0174. Min Act: -0.0001

Data Index: 1158359 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9667. Min Act: -0.0001

Data Index: 537386 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.2985. Min Range: -1.2985

Max Act: 1.0556. Min Act: -0.0001

Data Index: 1023225 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9446. Min Act: -0.0001

Data Index: 103142 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9627. Min Act: -0.0001

Data Index: 1237821 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9897. Min Act: -0.0001

Data Index: 988818 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9259. Min Act: -0.0001

Data Index: 10108 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8041. Min Act: -0.0001

Data Index: 605461 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8993. Min Act: -0.0001

Data Index: 18144 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8667. Min Act: -0.0001

Data Index: 913836 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9416. Min Act: -0.0001

Data Index: 1175281 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8990. Min Act: -0.0001

Data Index: 982415 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.9045. Min Act: -0.0001

Data Index: 255024 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1256744 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8974. Min Act: -0.0001

Data Index: 879760 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8137. Min Act: -0.0001

Data Index: 640735 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.2985. Min Range: -1.2985

Max Act: 0.8043. Min Act: -0.0001

Data Index: 1149186 (C4 (Web Text))

Max Activating Token Index: 219