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

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

Neuron 2008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6377. Min Act: -0.0001

Data Index: 878303 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7657. Min Act: -0.0001

Data Index: 586248 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7293. Min Act: -0.0001

Data Index: 1525885 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6654. Min Act: -0.0001

Data Index: 50046 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6107. Min Act: -0.0001

Data Index: 756940 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6922. Min Act: -0.0001

Data Index: 1393905 (Python Code)

Max Activating Token Index: 793

Text #6

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6222. Min Act: -0.0001

Data Index: 1371521 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6993. Min Act: -0.0001

Data Index: 1594433 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6314. Min Act: -0.0001

Data Index: 1538569 (Python Code)

Max Activating Token Index: 942

Text #9

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5782. Min Act: -0.0001

Data Index: 225045 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1135492 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5612. Min Act: -0.0001

Data Index: 756557 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1318135 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6674. Min Act: -0.0001

Data Index: 1508559 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.4829. Min Act: -0.0001

Data Index: 1583831 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5591. Min Act: -0.0001

Data Index: 1295257 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5523. Min Act: -0.0001

Data Index: 1580177 (Python Code)

Max Activating Token Index: 638

Text #17

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5268. Min Act: -0.0001

Data Index: 783172 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5448. Min Act: -0.0001

Data Index: 440578 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.5749. Min Act: -0.0001

Data Index: 37823 (C4 (Web Text))

Max Activating Token Index: 6