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

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

Neuron 1040 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.4632. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.5456. Min Act: -0.0000

Data Index: 865144 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.3692. Min Act: -0.0000

Data Index: 487721 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.3316. Min Act: -0.0000

Data Index: 1064202 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.1512. Min Act: -0.0000

Data Index: 405052 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.1255. Min Act: -0.0000

Data Index: 245872 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.1284. Min Act: -0.0000

Data Index: 339496 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.5131. Min Act: -0.0000

Data Index: 1159316 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.4373. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.4590. Min Act: -0.0000

Data Index: 1332115 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.2599. Min Act: -0.0000

Data Index: 1206393 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.9917. Min Act: -0.0000

Data Index: 1187586 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.8126. Min Act: -0.0000

Data Index: 780291 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 4.5456. Min Range: -4.5456

Max Act: 4.2105. Min Act: -0.0000

Data Index: 1324484 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.8316. Min Act: -0.0000

Data Index: 180047 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.9837. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.6119. Min Act: -0.0000

Data Index: 733164 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.7539. Min Act: -0.0000

Data Index: 350098 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.6980. Min Act: -0.0000

Data Index: 456736 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 4.5456. Min Range: -4.5456

Max Act: 3.6251. Min Act: -0.0000

Data Index: 670700 (C4 (Web Text))

Max Activating Token Index: 145