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

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

Neuron 4517 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: 1.2295. Min Range: -1.2295

Max Act: 1.1798. Min Act: -0.0000

Data Index: 632891 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.2295. Min Act: -0.0000

Data Index: 113581 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.0663. Min Act: -0.0000

Data Index: 473655 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.1851. Min Act: -0.0000

Data Index: 999876 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1264166 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.0592. Min Act: 0.0000

Data Index: 298037 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1161953 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9841. Min Act: -0.0000

Data Index: 135719 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9715. Min Act: -0.0000

Data Index: 418566 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1027390 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.8871. Min Act: -0.0000

Data Index: 974433 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9940. Min Act: -0.0000

Data Index: 497062 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9577. Min Act: -0.0000

Data Index: 775926 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1447631 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1400422 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1572907 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 1.2295. Min Range: -1.2295

Max Act: 1.0120. Min Act: -0.0000

Data Index: 250093 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1506304 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1577946 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 1.2295. Min Range: -1.2295

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1581073 (Python Code)

Max Activating Token Index: 83