Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1827 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.7080. Min Act: -0.0005

Data Index: 1053882 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4687. Min Act: -0.0005

Data Index: 1203044 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4591. Min Act: -0.0005

Data Index: 666250 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4841. Min Act: -0.0005

Data Index: 842974 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4706. Min Act: -0.0005

Data Index: 754435 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4506. Min Act: -0.0005

Data Index: 1062303 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4373. Min Act: -0.0005

Data Index: 1043666 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4384. Min Act: -0.0005

Data Index: 1233023 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4218. Min Act: -0.0005

Data Index: 1167050 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4476. Min Act: -0.0005

Data Index: 1141337 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4155. Min Act: -0.0005

Data Index: 1051349 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4282. Min Act: -0.0005

Data Index: 852285 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4381. Min Act: -0.0005

Data Index: 27858 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4211. Min Act: -0.0005

Data Index: 1122330 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4245. Min Act: -0.0005

Data Index: 127380 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4483. Min Act: -0.0005

Data Index: 151378 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4329. Min Act: -0.0005

Data Index: 452208 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4617. Min Act: -0.0005

Data Index: 1326170 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4278. Min Act: -0.0005

Data Index: 644117 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.4249. Min Act: -0.0005

Data Index: 274758 (C4 (Web Text))

Max Activating Token Index: 576