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

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

Neuron 2849 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.8881. Min Act: -0.0000

Data Index: 1001954 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.7045. Min Act: -0.0000

Data Index: 949264 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1312468 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1314196 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.5798. Min Act: -0.0000

Data Index: 876595 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.5959. Min Act: -0.0000

Data Index: 530794 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.7313. Min Act: -0.0000

Data Index: 1098345 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.5396. Min Act: -0.0000

Data Index: 561851 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1222811 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.5078. Min Act: -0.0000

Data Index: 315367 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.3851. Min Act: -0.0000

Data Index: 215622 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4645. Min Act: -0.0000

Data Index: 222763 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4644. Min Act: -0.0000

Data Index: 200939 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1271386 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4646. Min Act: -0.0000

Data Index: 681076 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1112139 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4380. Min Act: -0.0000

Data Index: 255809 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4265. Min Act: -0.0000

Data Index: 580224 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1017200 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.8881. Min Range: -1.8881

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1237198 (C4 (Web Text))

Max Activating Token Index: 853