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

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

Neuron 3541 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: 2.1389. Min Range: -2.1389

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1610454 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1389116 (Python Code)

Max Activating Token Index: 682

Text #2

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.9835. Min Act: -0.0000

Data Index: 1653134 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.7212. Min Act: -0.0000

Data Index: 1491293 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.8079. Min Act: -0.0000

Data Index: 1454349 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.8033. Min Act: -0.0000

Data Index: 761603 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.7861. Min Act: -0.0000

Data Index: 1486772 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6884. Min Act: -0.0000

Data Index: 1580539 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.7785. Min Act: -0.0000

Data Index: 1405713 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1626650 (Python Code)

Max Activating Token Index: 872

Text #10

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.8555. Min Act: -0.0000

Data Index: 1625122 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1620217 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6226. Min Act: -0.0000

Data Index: 1592058 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.8377. Min Act: -0.0000

Data Index: 1520745 (Python Code)

Max Activating Token Index: 799

Text #14

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1441447 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1627518 (Python Code)

Max Activating Token Index: 927

Text #16

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6961. Min Act: -0.0000

Data Index: 1627890 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6717. Min Act: -0.0000

Data Index: 1483002 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.5569. Min Act: -0.0000

Data Index: 1502356 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 2.1389. Min Range: -2.1389

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1508792 (Python Code)

Max Activating Token Index: 774