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

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

Neuron 73 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1061. Min Act: -0.0001

Data Index: 913616 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1062. Min Act: -0.0001

Data Index: 561795 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0977. Min Act: -0.0001

Data Index: 16852 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1298437 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1026. Min Act: -0.0001

Data Index: 90528 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0980. Min Act: -0.0001

Data Index: 130509 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0996. Min Act: -0.0001

Data Index: 585192 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1000. Min Act: -0.0001

Data Index: 335979 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1030. Min Act: -0.0001

Data Index: 919523 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0998. Min Act: -0.0001

Data Index: 360982 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1280335 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0951. Min Act: -0.0001

Data Index: 895298 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0951. Min Act: -0.0001

Data Index: 691710 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0953. Min Act: -0.0001

Data Index: 625773 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0973. Min Act: -0.0001

Data Index: 48971 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0937. Min Act: -0.0001

Data Index: 120485 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1198236 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0967. Min Act: -0.0001

Data Index: 908231 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0970. Min Act: -0.0001

Data Index: 591066 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1186651 (C4 (Web Text))

Max Activating Token Index: 171