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

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

Neuron 1023 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7992. Min Range: -7.7992

Max Act: 7.5354. Min Act: -0.0000

Data Index: 465547 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 7.7992. Min Range: -7.7992

Max Act: 7.5631. Min Act: -0.0000

Data Index: 917463 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 7.7992. Min Range: -7.7992

Max Act: 7.7992. Min Act: -0.0000

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 7.7992. Min Range: -7.7992

Max Act: 7.3752. Min Act: -0.0000

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 7.7992. Min Range: -7.7992

Max Act: 7.1619. Min Act: -0.0000

Data Index: 1087745 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.7762. Min Act: -0.0000

Data Index: 584781 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 7.7992. Min Range: -7.7992

Max Act: 7.3333. Min Act: -0.0000

Data Index: 29686 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.8251. Min Act: -0.0000

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.6622. Min Act: -0.0000

Data Index: 347088 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 7.7992. Min Range: -7.7992

Max Act: 7.0208. Min Act: -0.0000

Data Index: 1328676 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.7461. Min Act: -0.0000

Data Index: 52558 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.7254. Min Act: -0.0000

Data Index: 571136 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.1394. Min Act: -0.0000

Data Index: 891395 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.3685. Min Act: -0.0000

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.8998. Min Act: -0.0000

Data Index: 1243053 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.2434. Min Act: -0.0000

Data Index: 963282 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.7337. Min Act: -0.0000

Data Index: 734670 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.3272. Min Act: -0.0000

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.3239. Min Act: -0.0000

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 7.7992. Min Range: -7.7992

Max Act: 6.3634. Min Act: -0.0000

Data Index: 357277 (C4 (Web Text))

Max Activating Token Index: 853