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

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

Neuron 3223 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1996. Min Range: -2.1996

Max Act: 2.1996. Min Act: -0.0000

Data Index: 1617134 (Python Code)

Max Activating Token Index: 178

Text #1

Max Range: 2.1996. Min Range: -2.1996

Max Act: 2.1204. Min Act: -0.0000

Data Index: 1428171 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 2.1996. Min Range: -2.1996

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1578918 (Python Code)

Max Activating Token Index: 760

Text #3

Max Range: 2.1996. Min Range: -2.1996

Max Act: 2.0292. Min Act: -0.0000

Data Index: 1443283 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.9148. Min Act: -0.0000

Data Index: 1408588 (Python Code)

Max Activating Token Index: 855

Text #5

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.9557. Min Act: -0.0000

Data Index: 1390824 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1635486 (Python Code)

Max Activating Token Index: 71

Text #7

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.8610. Min Act: -0.0000

Data Index: 1518017 (Python Code)

Max Activating Token Index: 456

Text #8

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.9271. Min Act: -0.0000

Data Index: 1460700 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1587467 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.8025. Min Act: -0.0000

Data Index: 1422027 (Python Code)

Max Activating Token Index: 751

Text #11

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1413133 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1554401 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.8924. Min Act: -0.0000

Data Index: 1389647 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.8771. Min Act: -0.0000

Data Index: 1642671 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.7537. Min Act: -0.0000

Data Index: 1546680 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.7438. Min Act: -0.0000

Data Index: 1444442 (Python Code)

Max Activating Token Index: 614

Text #17

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.8409. Min Act: -0.0000

Data Index: 1643167 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.6026. Min Act: -0.0000

Data Index: 1499984 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 2.1996. Min Range: -2.1996

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1528023 (Python Code)

Max Activating Token Index: 680