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

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

Neuron 1118 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: 5.3769. Min Range: -5.3769

Max Act: 5.3769. Min Act: -0.0001

Data Index: 188925 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.6951. Min Act: -0.0001

Data Index: 1185415 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.6735. Min Act: -0.0001

Data Index: 985789 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.8044. Min Act: -0.0001

Data Index: 1317779 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.7172. Min Act: -0.0001

Data Index: 1159513 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.8546. Min Act: -0.0001

Data Index: 1312468 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.6029. Min Act: -0.0001

Data Index: 707685 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.5732. Min Act: -0.0001

Data Index: 242116 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.3095. Min Act: -0.0001

Data Index: 854113 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.4346. Min Act: -0.0001

Data Index: 866397 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.4352. Min Act: -0.0001

Data Index: 359820 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.2676. Min Act: -0.0001

Data Index: 465755 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 5.3769. Min Range: -5.3769

Max Act: 3.5167. Min Act: -0.0001

Data Index: 249412 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.2034. Min Act: -0.0001

Data Index: 710831 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.3286. Min Act: -0.0001

Data Index: 177710 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.3288. Min Act: -0.0001

Data Index: 1324633 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.0898. Min Act: -0.0001

Data Index: 714486 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.0489. Min Act: -0.0001

Data Index: 1095089 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.3912. Min Act: -0.0001

Data Index: 639984 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 5.3769. Min Range: -5.3769

Max Act: 4.0501. Min Act: -0.0001

Data Index: 825088 (C4 (Web Text))

Max Activating Token Index: 794