Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 308 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.4136. Min Act: -0.0001

Data Index: 634442 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1076546 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3976. Min Act: -0.0001

Data Index: 388244 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3813. Min Act: -0.0001

Data Index: 300697 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3854. Min Act: -0.0001

Data Index: 535203 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3872. Min Act: -0.0001

Data Index: 329264 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3607. Min Act: -0.0001

Data Index: 434731 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3680. Min Act: -0.0001

Data Index: 1153354 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1110642 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3770. Min Act: -0.0001

Data Index: 712196 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3748. Min Act: -0.0001

Data Index: 785749 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3858. Min Act: -0.0001

Data Index: 1168165 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3732. Min Act: -0.0001

Data Index: 237787 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3538. Min Act: -0.0001

Data Index: 891717 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3609. Min Act: -0.0001

Data Index: 23026 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3442. Min Act: -0.0001

Data Index: 516731 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3796. Min Act: -0.0001

Data Index: 1186142 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3562. Min Act: -0.0001

Data Index: 584998 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3499. Min Act: -0.0001

Data Index: 920698 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3778. Min Act: -0.0001

Data Index: 779190 (C4 (Web Text))

Max Activating Token Index: 306