Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2417 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6562. Min Act: -0.0000

Data Index: 188640 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6609. Min Act: -0.0000

Data Index: 117465 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1262560 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1151118 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1312384 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5480. Min Act: -0.0000

Data Index: 827842 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6675. Min Act: -0.0000

Data Index: 360551 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6748. Min Act: -0.0000

Data Index: 177259 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6233. Min Act: -0.0000

Data Index: 730176 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5555. Min Act: -0.0000

Data Index: 647467 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5864. Min Act: -0.0000

Data Index: 199071 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1272981 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6338. Min Act: -0.0000

Data Index: 862956 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1262389 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1013995 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5830. Min Act: -0.0000

Data Index: 895250 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5940. Min Act: -0.0000

Data Index: 417082 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1148016 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5424. Min Act: -0.0000

Data Index: 509862 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1260345 (C4 (Web Text))

Max Activating Token Index: 481