Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5121 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7498. Min Act: -0.0000

Data Index: 945335 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7019. Min Act: -0.0000

Data Index: 820385 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1266273 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1123987 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6485. Min Act: -0.0000

Data Index: 942857 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6903. Min Act: -0.0000

Data Index: 520770 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7121. Min Act: -0.0000

Data Index: 193680 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6373. Min Act: -0.0000

Data Index: 856310 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1105631 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6450. Min Act: -0.0000

Data Index: 164058 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6311. Min Act: -0.0000

Data Index: 204893 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6186. Min Act: -0.0000

Data Index: 291243 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1111501 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1119738 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5988. Min Act: -0.0000

Data Index: 723139 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6060. Min Act: -0.0000

Data Index: 735909 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5883. Min Act: -0.0000

Data Index: 642038 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5889. Min Act: -0.0000

Data Index: 645123 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5669. Min Act: -0.0000

Data Index: 336761 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1232462 (C4 (Web Text))

Max Activating Token Index: 576