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

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

Neuron 5850 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: 1.0970. Min Range: -1.0970

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1184340 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0186. Min Act: -0.0000

Data Index: 360996 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8829. Min Act: -0.0000

Data Index: 685162 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7957. Min Act: -0.0000

Data Index: 500754 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1533229 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8519. Min Act: -0.0000

Data Index: 102961 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7958. Min Act: -0.0000

Data Index: 14037 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8095. Min Act: -0.0000

Data Index: 512907 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7690. Min Act: -0.0000

Data Index: 543951 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7466. Min Act: -0.0000

Data Index: 498813 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7238. Min Act: -0.0000

Data Index: 7659 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7649. Min Act: -0.0000

Data Index: 424006 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1465950 (Python Code)

Max Activating Token Index: 289

Text #13

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7362. Min Act: -0.0000

Data Index: 739628 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7107. Min Act: -0.0000

Data Index: 538752 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1505732 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1626461 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1265181 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1332426 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1343772 (C4 (Web Text))

Max Activating Token Index: 151