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

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

Neuron 3048 in Layer 1

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: 0.4742. Min Range: -0.4742

Max Act: 0.4632. Min Act: -0.0002

Data Index: 19939 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4742. Min Act: -0.0002

Data Index: 433051 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4603. Min Act: -0.0002

Data Index: 996593 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4314. Min Act: -0.0002

Data Index: 760971 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4306. Min Act: -0.0002

Data Index: 891993 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4351. Min Act: -0.0002

Data Index: 982858 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4225. Min Act: -0.0002

Data Index: 117407 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4243. Min Act: -0.0002

Data Index: 593258 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4245. Min Act: -0.0002

Data Index: 265248 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4069. Min Act: -0.0002

Data Index: 541585 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4138. Min Act: -0.0002

Data Index: 961961 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4106. Min Act: -0.0002

Data Index: 1085335 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4055. Min Act: -0.0002

Data Index: 1169930 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3997. Min Act: -0.0002

Data Index: 996387 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4034. Min Act: -0.0002

Data Index: 969314 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3976. Min Act: -0.0002

Data Index: 953482 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3886. Min Act: -0.0002

Data Index: 1336432 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3943. Min Act: -0.0002

Data Index: 408057 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3996. Min Act: -0.0002

Data Index: 106120 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3936. Min Act: -0.0002

Data Index: 391482 (C4 (Web Text))

Max Activating Token Index: 220