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

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

Neuron 5095 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0728. Min Range: -2.0728

Max Act: 2.0728. Min Act: -0.0001

Data Index: 825936 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.9317. Min Act: -0.0000

Data Index: 784630 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1600534 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.8033. Min Act: -0.0000

Data Index: 1305461 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.6270. Min Act: -0.0000

Data Index: 1444513 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.6146. Min Act: -0.0000

Data Index: 173936 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.6057. Min Act: -0.0000

Data Index: 436522 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.6159. Min Act: -0.0000

Data Index: 1508717 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.4951. Min Act: -0.0000

Data Index: 1209247 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.5454. Min Act: -0.0000

Data Index: 330039 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.4772. Min Act: -0.0001

Data Index: 1572624 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.5172. Min Act: -0.0000

Data Index: 558293 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.3883. Min Act: -0.0000

Data Index: 808824 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.5160. Min Act: -0.0000

Data Index: 270093 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.4814. Min Act: -0.0001

Data Index: 442902 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1081274 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.4453. Min Act: -0.0000

Data Index: 456476 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.4602. Min Act: -0.0000

Data Index: 319876 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.5253. Min Act: -0.0000

Data Index: 433501 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 2.0728. Min Range: -2.0728

Max Act: 1.2921. Min Act: -0.0001

Data Index: 833257 (C4 (Web Text))

Max Activating Token Index: 857