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

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

Neuron 3686 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1238975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0492. Min Act: -0.0000

Data Index: 632802 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1607266 (Python Code)

Max Activating Token Index: 797

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1055964 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0474. Min Act: -0.0001

Data Index: 480557 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0424. Min Act: -0.0001

Data Index: 553412 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1369338 (Python Code)

Max Activating Token Index: 880

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0430. Min Act: -0.0001

Data Index: 841344 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1003149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1306447 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0414. Min Act: -0.0001

Data Index: 227573 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1044630 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1140408 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1090691 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0411. Min Act: -0.0001

Data Index: 153387 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1436118 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0428. Min Act: -0.0001

Data Index: 122461 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0378. Min Act: -0.0001

Data Index: 832497 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0434. Min Act: -0.0001

Data Index: 689768 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1381057 (Python Code)

Max Activating Token Index: 637