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

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

Neuron 336 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.9448. Min Act: -0.0000

Data Index: 527821 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8996. Min Act: -0.0000

Data Index: 1420767 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.6001. Min Act: -0.0000

Data Index: 987945 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8951. Min Act: -0.0000

Data Index: 862531 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.7081. Min Act: -0.0000

Data Index: 696897 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8287. Min Act: -0.0000

Data Index: 306854 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.6878. Min Act: -0.0000

Data Index: 237122 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8167. Min Act: -0.0000

Data Index: 788196 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8301. Min Act: -0.0000

Data Index: 1449768 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.6907. Min Act: -0.0000

Data Index: 1293339 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.7009. Min Act: -0.0000

Data Index: 769950 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8416. Min Act: -0.0000

Data Index: 1093214 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8791. Min Act: -0.0000

Data Index: 640054 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.7858. Min Act: -0.0000

Data Index: 1046920 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.9217. Min Act: -0.0000

Data Index: 840700 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8061. Min Act: -0.0000

Data Index: 1215880 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8577. Min Act: -0.0000

Data Index: 1595578 (Python Code)

Max Activating Token Index: 644

Text #17

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.6136. Min Act: -0.0000

Data Index: 172110 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.7998. Min Act: -0.0000

Data Index: 559025 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.9448. Min Range: -1.9448

Max Act: 1.8003. Min Act: -0.0000

Data Index: 173010 (C4 (Web Text))

Max Activating Token Index: 631