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

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

Neuron 1370 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3981. Min Act: -0.0001

Data Index: 867664 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3142. Min Act: -0.0000

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3052. Min Act: -0.0001

Data Index: 904592 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2973. Min Act: -0.0000

Data Index: 193977 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3361. Min Act: -0.0001

Data Index: 810312 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3110. Min Act: -0.0000

Data Index: 425121 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3314. Min Act: -0.0000

Data Index: 255684 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2863. Min Act: -0.0000

Data Index: 110471 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3028. Min Act: -0.0000

Data Index: 538365 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1240419 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3094. Min Act: -0.0000

Data Index: 994792 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3095. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2897. Min Act: -0.0000

Data Index: 741384 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2762. Min Act: -0.0000

Data Index: 313792 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2701. Min Act: -0.0000

Data Index: 42221 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2537. Min Act: -0.0001

Data Index: 373680 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2557. Min Act: -0.0000

Data Index: 827615 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2621. Min Act: -0.0000

Data Index: 362708 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2805. Min Act: -0.0000

Data Index: 198885 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2615. Min Act: -0.0001

Data Index: 896957 (C4 (Web Text))

Max Activating Token Index: 687