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

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

Neuron 3409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8898. Min Act: -0.0000

Data Index: 585736 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6840. Min Act: -0.0000

Data Index: 65908 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1347848 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7293. Min Act: 0.0000

Data Index: 1613261 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6763. Min Act: -0.0000

Data Index: 363800 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6636. Min Act: -0.0000

Data Index: 538492 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6289. Min Act: -0.0000

Data Index: 111862 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1391091 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1466562 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5825. Min Act: -0.0001

Data Index: 1413095 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5972. Min Act: -0.0000

Data Index: 818658 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6312. Min Act: -0.0000

Data Index: 701879 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1494610 (Python Code)

Max Activating Token Index: 659

Text #13

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5819. Min Act: -0.0001

Data Index: 1509173 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1121846 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1637888 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5752. Min Act: -0.0001

Data Index: 1422822 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5935. Min Act: -0.0000

Data Index: 35322 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5615. Min Act: 0.0001

Data Index: 1419917 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5458. Min Act: 0.0000

Data Index: 1624459 (Python Code)

Max Activating Token Index: 442