Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4605 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1005131 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1236464 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.6320. Min Act: -0.0000

Data Index: 485703 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5719. Min Act: -0.0000

Data Index: 860474 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5776. Min Act: -0.0001

Data Index: 1125142 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5006. Min Act: -0.0000

Data Index: 756360 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5462. Min Act: -0.0000

Data Index: 285159 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5383. Min Act: -0.0000

Data Index: 929892 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5076. Min Act: -0.0000

Data Index: 730500 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5415. Min Act: -0.0000

Data Index: 220133 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5172. Min Act: -0.0000

Data Index: 526022 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1034601 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.5701. Min Act: -0.0000

Data Index: 214375 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1046166 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1034242 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4883. Min Act: -0.0000

Data Index: 625347 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4964. Min Act: -0.0000

Data Index: 311670 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1070671 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4667. Min Act: -0.0000

Data Index: 874010 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.8059. Min Range: -0.8059

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1048075 (C4 (Web Text))

Max Activating Token Index: 15