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

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

Neuron 2363 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: 2.8400. Min Range: -2.8400

Max Act: 2.8226. Min Act: -0.0000

Data Index: 1464210 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.8400. Min Act: -0.0000

Data Index: 1406705 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.8292. Min Act: -0.0000

Data Index: 1475678 (Python Code)

Max Activating Token Index: 547

Text #3

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.7747. Min Act: -0.0000

Data Index: 1406596 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.6220. Min Act: -0.0000

Data Index: 1323815 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.7357. Min Act: -0.0000

Data Index: 1549042 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.4925. Min Act: -0.0000

Data Index: 1608204 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.4679. Min Act: -0.0000

Data Index: 1559743 (Python Code)

Max Activating Token Index: 292

Text #8

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.5784. Min Act: -0.0000

Data Index: 1617996 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.5890. Min Act: -0.0000

Data Index: 1370409 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.5649. Min Act: -0.0000

Data Index: 1374772 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.5223. Min Act: -0.0000

Data Index: 1643723 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.5063. Min Act: -0.0000

Data Index: 1363549 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.4957. Min Act: -0.0000

Data Index: 1512271 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.4860. Min Act: -0.0000

Data Index: 1381262 (Python Code)

Max Activating Token Index: 692

Text #15

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.6038. Min Act: -0.0000

Data Index: 1363332 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.3305. Min Act: -0.0000

Data Index: 563598 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.5448. Min Act: -0.0000

Data Index: 1540349 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1433734 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 2.8400. Min Range: -2.8400

Max Act: 2.5371. Min Act: -0.0000

Data Index: 203906 (C4 (Web Text))

Max Activating Token Index: 927