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

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

Neuron 1171 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.5054. Min Act: -0.0003

Data Index: 695879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3907. Min Act: -0.0003

Data Index: 296084 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3856. Min Act: -0.0003

Data Index: 1361789 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3880. Min Act: -0.0003

Data Index: 812474 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3680. Min Act: -0.0003

Data Index: 1101781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3546. Min Act: -0.0003

Data Index: 1217181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3669. Min Act: -0.0003

Data Index: 359757 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3678. Min Act: -0.0003

Data Index: 309473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3485. Min Act: -0.0003

Data Index: 1360066 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3632. Min Act: -0.0003

Data Index: 1313358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3527. Min Act: -0.0003

Data Index: 419833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3196. Min Act: -0.0003

Data Index: 54117 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3169. Min Act: -0.0003

Data Index: 156116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3171. Min Act: -0.0003

Data Index: 1442213 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2939. Min Act: -0.0003

Data Index: 142741 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2857. Min Act: -0.0003

Data Index: 727991 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.2831. Min Act: -0.0003

Data Index: 198638 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3282. Min Act: -0.0003

Data Index: 745785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3179. Min Act: -0.0003

Data Index: 1575902 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3207. Min Act: -0.0003

Data Index: 1092623 (C4 (Web Text))

Max Activating Token Index: 1023