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

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

Neuron 3495 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: 1.3926. Min Range: -1.3926

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1491532 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1551564 (Python Code)

Max Activating Token Index: 456

Text #2

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1487855 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1576255 (Python Code)

Max Activating Token Index: 629

Text #4

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1526444 (Python Code)

Max Activating Token Index: 631

Text #5

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1652151 (Python Code)

Max Activating Token Index: 334

Text #6

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1397435 (Python Code)

Max Activating Token Index: 805

Text #7

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1477119 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1509306 (Python Code)

Max Activating Token Index: 914

Text #9

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1514118 (Python Code)

Max Activating Token Index: 212

Text #10

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1540337 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1448446 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1541942 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1561036 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1568349 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1491053 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1422315 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1585784 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1584165 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1426304 (Python Code)

Max Activating Token Index: 770