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

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

Neuron 1218 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1185351 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.0934. Min Act: -0.0000

Data Index: 911413 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1322745 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1389. Min Act: 0.0000

Data Index: 179608 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1029266 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2147. Min Act: -0.0000

Data Index: 859374 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1465639 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1498937 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1138. Min Act: 0.0000

Data Index: 1606672 (Python Code)

Max Activating Token Index: 545

Text #9

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1389987 (Python Code)

Max Activating Token Index: 691

Text #10

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1181. Min Act: -0.0000

Data Index: 682731 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1371. Min Act: -0.0000

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1133. Min Act: -0.0000

Data Index: 30515 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1198. Min Act: -0.0000

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1149. Min Act: -0.0000

Data Index: 479590 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1053. Min Act: -0.0000

Data Index: 46618 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1469100 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1102. Min Act: 0.0000

Data Index: 828349 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1122. Min Act: -0.0000

Data Index: 121890 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1620680 (Python Code)

Max Activating Token Index: 879