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

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

Neuron 2485 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0000

Data Index: 716438 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1314596 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1463312 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1165. Min Act: -0.0000

Data Index: 547984 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0996. Min Act: -0.0000

Data Index: 78886 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1487434 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1466188 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1023. Min Act: -0.0000

Data Index: 438476 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1576625 (Python Code)

Max Activating Token Index: 806

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0925. Min Act: -0.0000

Data Index: 903892 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1031. Min Act: -0.0000

Data Index: 21698 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1447574 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1422919 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1181749 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1502894 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0973. Min Act: -0.0000

Data Index: 987991 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0930. Min Act: -0.0000

Data Index: 681810 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1022093 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1472120 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1010542 (C4 (Web Text))

Max Activating Token Index: 729