Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3265 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1627133 (Python Code)

Max Activating Token Index: 939

Text #1

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2838. Min Act: -0.0001

Data Index: 888375 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2899. Min Act: -0.0001

Data Index: 1372638 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2748. Min Act: -0.0001

Data Index: 406680 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2833. Min Act: -0.0000

Data Index: 602510 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1516940 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2556. Min Act: -0.0001

Data Index: 821875 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2844. Min Act: -0.0001

Data Index: 956500 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2651. Min Act: -0.0001

Data Index: 1527295 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2464. Min Act: -0.0001

Data Index: 698902 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2694. Min Act: -0.0001

Data Index: 692679 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2511. Min Act: -0.0001

Data Index: 100228 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2580. Min Act: -0.0001

Data Index: 817172 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2482. Min Act: -0.0001

Data Index: 609949 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2635. Min Act: -0.0001

Data Index: 1309539 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1294054 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2510. Min Act: -0.0001

Data Index: 610251 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1456058 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2578. Min Act: -0.0001

Data Index: 813744 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1152993 (C4 (Web Text))

Max Activating Token Index: 349