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

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

Neuron 3394 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.4847. Min Act: -0.0000

Data Index: 1622370 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.1794. Min Act: -0.0000

Data Index: 1427522 (Python Code)

Max Activating Token Index: 968

Text #2

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.1530. Min Act: -0.0000

Data Index: 1568298 (Python Code)

Max Activating Token Index: 904

Text #3

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.0465. Min Act: -0.0000

Data Index: 1361473 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.2773. Min Act: -0.0000

Data Index: 1562240 (Python Code)

Max Activating Token Index: 992

Text #5

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.2869. Min Act: 0.0000

Data Index: 302365 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.1143. Min Act: -0.0000

Data Index: 1428149 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.8896. Min Act: -0.0000

Data Index: 1513293 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.1415. Min Act: -0.0000

Data Index: 1066282 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.1692. Min Act: -0.0000

Data Index: 1644400 (Python Code)

Max Activating Token Index: 733

Text #10

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1631960 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 2.4847. Min Range: -2.4847

Max Act: 2.0350. Min Act: -0.0000

Data Index: 941543 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1592985 (Python Code)

Max Activating Token Index: 571

Text #13

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1411720 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.8227. Min Act: -0.0000

Data Index: 82361 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.9142. Min Act: -0.0000

Data Index: 604483 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1233270 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.4731. Min Act: -0.0000

Data Index: 601683 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.7877. Min Act: -0.0000

Data Index: 1095430 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 2.4847. Min Range: -2.4847

Max Act: 1.7969. Min Act: -0.0000

Data Index: 128782 (C4 (Web Text))

Max Activating Token Index: 260