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

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

Neuron 5870 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: 2.3839. Min Range: -2.3839

Max Act: 2.3839. Min Act: -0.0001

Data Index: 925118 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.3160. Min Act: -0.0001

Data Index: 1159099 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2705. Min Act: -0.0001

Data Index: 116303 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.3398. Min Act: -0.0001

Data Index: 1019631 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2497. Min Act: -0.0001

Data Index: 38546 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2319. Min Act: -0.0002

Data Index: 820955 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2382. Min Act: -0.0001

Data Index: 660224 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2254. Min Act: -0.0001

Data Index: 856710 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2757. Min Act: -0.0001

Data Index: 462916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2304. Min Act: -0.0001

Data Index: 972151 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.3194. Min Act: -0.0001

Data Index: 792382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2276. Min Act: -0.0002

Data Index: 370681 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.1999. Min Act: -0.0001

Data Index: 265839 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.1944. Min Act: -0.0001

Data Index: 1313054 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2029. Min Act: -0.0001

Data Index: 986773 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.1922. Min Act: -0.0001

Data Index: 360215 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.1910. Min Act: -0.0001

Data Index: 1272199 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.1698. Min Act: -0.0001

Data Index: 750135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2412. Min Act: -0.0001

Data Index: 1125001 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 2.3839. Min Range: -2.3839

Max Act: 2.2366. Min Act: -0.0001

Data Index: 1149343 (C4 (Web Text))

Max Activating Token Index: 1023