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

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

Neuron 604 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1278932 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4877. Min Act: -0.0000

Data Index: 847324 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4875. Min Act: -0.0000

Data Index: 25549 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4310. Min Act: -0.0000

Data Index: 805765 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4491. Min Act: -0.0000

Data Index: 476371 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1274803 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3959. Min Act: -0.0000

Data Index: 87429 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4129. Min Act: -0.0000

Data Index: 395481 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4235. Min Act: -0.0000

Data Index: 831964 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3518. Min Act: -0.0000

Data Index: 875112 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.4098. Min Act: -0.0000

Data Index: 970242 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1143769 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3927. Min Act: -0.0000

Data Index: 775132 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3866. Min Act: -0.0000

Data Index: 434174 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1563 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3950. Min Act: -0.0000

Data Index: 739283 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1039510 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3575. Min Act: -0.0000

Data Index: 65322 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3690. Min Act: -0.0000

Data Index: 869477 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.5972. Min Range: -0.5972

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1232364 (C4 (Web Text))

Max Activating Token Index: 227