Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 833 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0004

Data Index: 98254 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0939. Min Act: -0.0004

Data Index: 416289 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0937. Min Act: -0.0004

Data Index: 434751 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0748. Min Act: -0.0004

Data Index: 966907 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0957. Min Act: -0.0004

Data Index: 346952 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0954. Min Act: -0.0004

Data Index: 443374 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0875. Min Act: -0.0004

Data Index: 768098 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0905. Min Act: -0.0004

Data Index: 655788 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0934. Min Act: -0.0004

Data Index: 731787 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0900. Min Act: -0.0004

Data Index: 395694 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0894. Min Act: -0.0004

Data Index: 264749 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0858. Min Act: -0.0004

Data Index: 899864 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0890. Min Act: -0.0004

Data Index: 1200748 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0783. Min Act: -0.0004

Data Index: 248245 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0879. Min Act: -0.0004

Data Index: 646705 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0769. Min Act: -0.0004

Data Index: 1221307 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0860. Min Act: -0.0004

Data Index: 258486 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0955. Min Act: -0.0004

Data Index: 1061009 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0845. Min Act: -0.0004

Data Index: 265076 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0804. Min Act: -0.0004

Data Index: 365586 (C4 (Web Text))

Max Activating Token Index: 125