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

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

Neuron 2704 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: 4.6083. Min Range: -4.6083

Max Act: 4.6083. Min Act: -0.0000

Data Index: 959176 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.4488. Min Act: -0.0000

Data Index: 351903 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.4014. Min Act: -0.0000

Data Index: 281463 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.4546. Min Act: -0.0000

Data Index: 1307376 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.2807. Min Act: -0.0000

Data Index: 890078 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.2735. Min Act: -0.0000

Data Index: 616182 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.4197. Min Act: -0.0000

Data Index: 362819 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.0738. Min Act: -0.0000

Data Index: 625884 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.1403. Min Act: -0.0000

Data Index: 241023 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.1307. Min Act: -0.0000

Data Index: 1090912 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.1385. Min Act: -0.0000

Data Index: 380354 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.0829. Min Act: -0.0000

Data Index: 895674 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8714. Min Act: -0.0000

Data Index: 233744 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.0924. Min Act: -0.0000

Data Index: 862251 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 4.6083. Min Range: -4.6083

Max Act: 3.0061. Min Act: -0.0000

Data Index: 93584 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8516. Min Act: -0.0000

Data Index: 304545 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.6959. Min Act: -0.0000

Data Index: 1198678 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8174. Min Act: -0.0000

Data Index: 74039 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8125. Min Act: -0.0000

Data Index: 50719 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 4.6083. Min Range: -4.6083

Max Act: 2.8009. Min Act: -0.0000

Data Index: 816430 (C4 (Web Text))

Max Activating Token Index: 834