Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1418626 (Python Code)

Max Activating Token Index: 901

Text #1

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4782. Min Act: -0.0000

Data Index: 252687 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4490. Min Act: -0.0000

Data Index: 322392 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1582771 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4143. Min Act: -0.0000

Data Index: 490192 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1228882 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4258. Min Act: -0.0000

Data Index: 840513 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1037696 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4096. Min Act: -0.0000

Data Index: 666924 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4097. Min Act: -0.0000

Data Index: 424630 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1361505 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1253454 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3956. Min Act: -0.0000

Data Index: 527069 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4062. Min Act: -0.0000

Data Index: 882980 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1107225 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3806. Min Act: -0.0000

Data Index: 256168 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1363676 (Python Code)

Max Activating Token Index: 488

Text #17

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1338119 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1545264 (Python Code)

Max Activating Token Index: 364

Text #19

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1486590 (Python Code)

Max Activating Token Index: 805