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

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

Neuron 4458 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: 0.5661. Min Range: -0.5661

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1253758 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1025651 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4170. Min Act: -0.0000

Data Index: 153596 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3722. Min Act: -0.0000

Data Index: 32509 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4523. Min Act: -0.0000

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3980. Min Act: -0.0000

Data Index: 79109 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3964. Min Act: -0.0000

Data Index: 602903 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4095. Min Act: -0.0000

Data Index: 361417 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3963. Min Act: -0.0000

Data Index: 51320 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4713. Min Act: -0.0000

Data Index: 800412 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1344888 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3984. Min Act: -0.0000

Data Index: 321860 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1027530 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4013. Min Act: -0.0000

Data Index: 235090 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4298. Min Act: -0.0000

Data Index: 745916 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3906. Min Act: -0.0000

Data Index: 637021 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3658. Min Act: -0.0000

Data Index: 529327 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3946. Min Act: -0.0000

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3703. Min Act: -0.0000

Data Index: 344158 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1222421 (C4 (Web Text))

Max Activating Token Index: 82