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

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

Neuron 5017 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2598. Min Act: -0.0001

Data Index: 62865 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2542. Min Act: -0.0001

Data Index: 1172258 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2562. Min Act: -0.0001

Data Index: 292343 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2284. Min Act: -0.0001

Data Index: 452928 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2215. Min Act: -0.0001

Data Index: 39414 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2280. Min Act: -0.0001

Data Index: 115166 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2149. Min Act: -0.0001

Data Index: 72028 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2117. Min Act: -0.0001

Data Index: 475968 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2096. Min Act: -0.0001

Data Index: 533612 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2048. Min Act: -0.0001

Data Index: 885786 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.2040. Min Act: -0.0001

Data Index: 926650 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1993. Min Act: -0.0001

Data Index: 612734 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1997. Min Act: -0.0001

Data Index: 768867 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1999. Min Act: -0.0001

Data Index: 139119 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1966. Min Act: -0.0001

Data Index: 480927 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1931. Min Act: -0.0001

Data Index: 36683 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1883. Min Act: -0.0001

Data Index: 246507 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1916. Min Act: -0.0001

Data Index: 202914 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1876. Min Act: -0.0001

Data Index: 654849 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.2598. Min Range: -0.2598

Max Act: 0.1760. Min Act: -0.0001

Data Index: 624002 (C4 (Web Text))

Max Activating Token Index: 73