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

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

Neuron 871 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: 0.6123. Min Range: -0.6123

Max Act: 0.5969. Min Act: -0.0000

Data Index: 300533 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.6123. Min Act: -0.0000

Data Index: 650213 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1335550 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4065. Min Act: -0.0000

Data Index: 377848 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1412187 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1541541 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1206378 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2906. Min Act: -0.0000

Data Index: 744358 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1631406 (Python Code)

Max Activating Token Index: 918

Text #9

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2948. Min Act: -0.0000

Data Index: 775954 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1450183 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2779. Min Act: -0.0000

Data Index: 923171 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2929. Min Act: -0.0000

Data Index: 695206 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1290441 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2768. Min Act: -0.0000

Data Index: 270648 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2819. Min Act: -0.0000

Data Index: 652149 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1430643 (Python Code)

Max Activating Token Index: 844

Text #17

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1137972 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1579456 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1445407 (Python Code)

Max Activating Token Index: 845