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

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

Neuron 610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1250. Min Act: -0.0002

Data Index: 66355 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1089. Min Act: -0.0002

Data Index: 461955 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.2525. Min Act: -0.0002

Data Index: 754638 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.2437. Min Act: -0.0002

Data Index: 256417 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.0936. Min Act: -0.0002

Data Index: 1024121 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1962. Min Act: -0.0002

Data Index: 1121921 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.0328. Min Act: -0.0002

Data Index: 798112 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.0950. Min Act: -0.0002

Data Index: 1169631 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.0847. Min Act: -0.0002

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1048. Min Act: -0.0002

Data Index: 812532 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1400. Min Act: -0.0002

Data Index: 472622 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.2003. Min Act: -0.0002

Data Index: 262573 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1316. Min Act: -0.0002

Data Index: 399865 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.2643. Min Act: -0.0002

Data Index: 279294 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.0052. Min Act: -0.0002

Data Index: 959302 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1581. Min Act: -0.0002

Data Index: 1283237 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.0914. Min Act: -0.0002

Data Index: 1128598 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.0900. Min Act: -0.0002

Data Index: 1116214 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1553. Min Act: -0.0002

Data Index: 301911 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 1.2643. Min Range: -1.2643

Max Act: 1.1403. Min Act: -0.0002

Data Index: 599199 (C4 (Web Text))

Max Activating Token Index: 184