Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2246 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1382. Min Range: -1.1382

Max Act: 1.1113. Min Act: -0.0001

Data Index: 1501748 (Python Code)

Max Activating Token Index: 481

Text #1

Max Range: 1.1382. Min Range: -1.1382

Max Act: 1.1382. Min Act: -0.0001

Data Index: 1551273 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.9731. Min Act: -0.0001

Data Index: 1588776 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.9728. Min Act: -0.0001

Data Index: 1549992 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.9771. Min Act: -0.0001

Data Index: 1466133 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.8745. Min Act: -0.0001

Data Index: 1555271 (Python Code)

Max Activating Token Index: 530

Text #6

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.8250. Min Act: -0.0001

Data Index: 1508355 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1544571 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1656981 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1438371 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7942. Min Act: -0.0001

Data Index: 1419727 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1622165 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1575088 (Python Code)

Max Activating Token Index: 982

Text #13

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7362. Min Act: -0.0001

Data Index: 1520125 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1573157 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7270. Min Act: -0.0001

Data Index: 1617773 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7455. Min Act: -0.0001

Data Index: 1401142 (Python Code)

Max Activating Token Index: 341

Text #17

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1473395 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7340. Min Act: -0.0001

Data Index: 1522634 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 1.1382. Min Range: -1.1382

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1584234 (Python Code)

Max Activating Token Index: 175