Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 786 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2669. Min Act: -0.0001

Data Index: 296423 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2566. Min Act: -0.0001

Data Index: 1142302 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2473. Min Act: -0.0000

Data Index: 878957 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1244309 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2208. Min Act: -0.0000

Data Index: 45470 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2121. Min Act: -0.0001

Data Index: 500334 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1174104 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2298. Min Act: -0.0001

Data Index: 122860 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1279075 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1003353 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2194. Min Act: -0.0001

Data Index: 885734 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2033. Min Act: -0.0000

Data Index: 487531 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2105. Min Act: -0.0000

Data Index: 487896 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2023. Min Act: -0.0000

Data Index: 727297 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1979. Min Act: -0.0000

Data Index: 601608 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2042. Min Act: -0.0001

Data Index: 433000 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1987. Min Act: -0.0000

Data Index: 877734 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1951. Min Act: -0.0000

Data Index: 986160 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1086817 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.1889. Min Act: -0.0001

Data Index: 860112 (C4 (Web Text))

Max Activating Token Index: 858