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

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

Neuron 3698 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9552. Min Act: -0.0000

Data Index: 171969 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9133. Min Act: -0.0000

Data Index: 516200 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9239. Min Act: -0.0000

Data Index: 402202 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9072. Min Act: -0.0000

Data Index: 594953 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8974. Min Act: -0.0000

Data Index: 519140 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1284109 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9013. Min Act: -0.0000

Data Index: 252836 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9410. Min Act: -0.0000

Data Index: 363982 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8928. Min Act: -0.0000

Data Index: 700812 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8321. Min Act: -0.0000

Data Index: 891475 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1344602 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8401. Min Act: -0.0000

Data Index: 447965 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7297. Min Act: -0.0000

Data Index: 25693 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8259. Min Act: -0.0000

Data Index: 532052 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1298132 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1061134 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1160256 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1284648 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8061. Min Act: -0.0000

Data Index: 560831 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1332222 (C4 (Web Text))

Max Activating Token Index: 37