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

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

Neuron 463 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0831. Min Range: -3.0831

Max Act: 3.0831. Min Act: -0.0000

Data Index: 920089 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.5367. Min Act: -0.0000

Data Index: 288148 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.4652. Min Act: -0.0000

Data Index: 714810 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.3153. Min Act: -0.0000

Data Index: 425007 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.4959. Min Act: -0.0000

Data Index: 1305027 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.4934. Min Act: -0.0000

Data Index: 1139823 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.3592. Min Act: -0.0000

Data Index: 417649 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.2388. Min Act: -0.0000

Data Index: 989355 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.3173. Min Act: -0.0000

Data Index: 87985 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.1926. Min Act: -0.0000

Data Index: 322173 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.1907. Min Act: -0.0000

Data Index: 1117422 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.1495. Min Act: -0.0000

Data Index: 372779 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.2146. Min Act: -0.0000

Data Index: 867037 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 3.0831. Min Range: -3.0831

Max Act: 1.7817. Min Act: -0.0000

Data Index: 1125254 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.2191. Min Act: -0.0000

Data Index: 1231754 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.1063. Min Act: -0.0000

Data Index: 1103190 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.2276. Min Act: -0.0000

Data Index: 922148 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.2013. Min Act: -0.0000

Data Index: 426985 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.0622. Min Act: -0.0000

Data Index: 1323777 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 3.0831. Min Range: -3.0831

Max Act: 2.2960. Min Act: -0.0000

Data Index: 337245 (C4 (Web Text))

Max Activating Token Index: 379