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

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

Neuron 3380 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.5455. Min Act: -0.0000

Data Index: 304641 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.5182. Min Act: -0.0000

Data Index: 769037 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1923 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.4884. Min Act: -0.0000

Data Index: 394305 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.4439. Min Act: -0.0000

Data Index: 607715 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1179578 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.4253. Min Act: -0.0000

Data Index: 407993 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3766. Min Act: -0.0000

Data Index: 305085 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3438. Min Act: -0.0000

Data Index: 512211 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1153784 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3323. Min Act: -0.0000

Data Index: 35007 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1116687 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3160. Min Act: -0.0000

Data Index: 233807 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3010. Min Act: -0.0000

Data Index: 555559 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.2950. Min Act: -0.0000

Data Index: 847326 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.3039. Min Act: -0.0000

Data Index: 768355 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.2971. Min Act: -0.0000

Data Index: 680373 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.2863. Min Act: -0.0000

Data Index: 25459 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.2806. Min Act: -0.0000

Data Index: 719915 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.5455. Min Range: -0.5455

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1188447 (C4 (Web Text))

Max Activating Token Index: 661