Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1087. Min Act: -0.0000

Data Index: 396383 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1008535 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1066. Min Act: -0.0000

Data Index: 517234 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1100. Min Act: -0.0000

Data Index: 96835 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1027. Min Act: -0.0000

Data Index: 504452 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0975. Min Act: -0.0000

Data Index: 367749 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0965. Min Act: -0.0000

Data Index: 932425 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1030782 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0930. Min Act: -0.0000

Data Index: 176216 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0916. Min Act: -0.0000

Data Index: 511279 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0911. Min Act: -0.0000

Data Index: 557007 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0830. Min Act: -0.0000

Data Index: 581875 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1372032 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1602719 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1235740 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0772. Min Act: -0.0000

Data Index: 971951 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0807. Min Act: -0.0000

Data Index: 329257 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0869. Min Act: -0.0000

Data Index: 169669 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1395771 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1633714 (Python Code)

Max Activating Token Index: 451