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

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

Neuron 728 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7809. Min Act: -0.0000

Data Index: 582713 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7820. Min Act: 0.0000

Data Index: 1307438 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1159880 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1250839 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7505. Min Act: -0.0000

Data Index: 550771 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8034. Min Act: -0.0000

Data Index: 151384 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8028. Min Act: -0.0000

Data Index: 346361 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7801. Min Act: -0.0000

Data Index: 207200 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1299301 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1318781 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7644. Min Act: -0.0000

Data Index: 582377 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7664. Min Act: -0.0000

Data Index: 852479 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7583. Min Act: -0.0000

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7674. Min Act: -0.0000

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1219503 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7439. Min Act: -0.0000

Data Index: 513405 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7681. Min Act: -0.0000

Data Index: 316017 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1491600 (Python Code)

Max Activating Token Index: 326

Text #19

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7178. Min Act: -0.0000

Data Index: 863871 (C4 (Web Text))

Max Activating Token Index: 126