Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3144 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1054534 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3885. Min Act: -0.0000

Data Index: 298417 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1461560 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3513. Min Act: -0.0000

Data Index: 740097 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1084614 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1626663 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1378985 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1590783 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1539582 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1236336 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1283360 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1633896 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1536195 (Python Code)

Max Activating Token Index: 783

Text #13

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1327105 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2742. Min Act: -0.0000

Data Index: 316413 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1533002 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1106970 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1529887 (Python Code)

Max Activating Token Index: 798

Text #18

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1450691 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2863. Min Act: -0.0000

Data Index: 325350 (C4 (Web Text))

Max Activating Token Index: 75