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

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

Neuron 2195 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1246476 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1000271 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1352632 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7081. Min Act: -0.0000

Data Index: 645917 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6831. Min Act: -0.0000

Data Index: 918095 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7037. Min Act: -0.0000

Data Index: 325054 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6807. Min Act: -0.0001

Data Index: 275129 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6776. Min Act: -0.0000

Data Index: 612596 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6452. Min Act: -0.0001

Data Index: 134837 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1301018 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7038. Min Act: -0.0000

Data Index: 94806 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1108720 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6242. Min Act: -0.0001

Data Index: 606003 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5969. Min Act: -0.0000

Data Index: 516101 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6363. Min Act: -0.0001

Data Index: 858265 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6572. Min Act: -0.0001

Data Index: 829497 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6091. Min Act: -0.0000

Data Index: 66215 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6009. Min Act: -0.0000

Data Index: 169513 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6454. Min Act: -0.0000

Data Index: 887616 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5727. Min Act: -0.0000

Data Index: 457051 (C4 (Web Text))

Max Activating Token Index: 138