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

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

Neuron 2299 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: 1.3940. Min Range: -1.3940

Max Act: 1.3940. Min Act: -0.0001

Data Index: 900091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.3699. Min Act: -0.0001

Data Index: 792065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.3222. Min Act: -0.0001

Data Index: 881897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.3035. Min Act: -0.0001

Data Index: 762557 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2470. Min Act: -0.0001

Data Index: 1327325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2706. Min Act: -0.0001

Data Index: 532040 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2549. Min Act: -0.0001

Data Index: 1016767 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2484. Min Act: -0.0001

Data Index: 366900 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2465. Min Act: -0.0001

Data Index: 478005 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2508. Min Act: -0.0001

Data Index: 996452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2497. Min Act: -0.0001

Data Index: 1304203 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2209. Min Act: -0.0001

Data Index: 114918 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2318. Min Act: -0.0001

Data Index: 967899 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2221. Min Act: -0.0001

Data Index: 316503 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.1988. Min Act: -0.0001

Data Index: 1225796 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2025. Min Act: -0.0001

Data Index: 690687 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2258. Min Act: -0.0001

Data Index: 87326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.1943. Min Act: -0.0001

Data Index: 727111 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2160. Min Act: -0.0001

Data Index: 1324547 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.3940. Min Range: -1.3940

Max Act: 1.2070. Min Act: -0.0001

Data Index: 1332682 (C4 (Web Text))

Max Activating Token Index: 1023