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

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

Neuron 2680 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9837. Min Act: 0.0000

Data Index: 1420414 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9968. Min Act: 0.0001

Data Index: 1548250 (Python Code)

Max Activating Token Index: 424

Text #2

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9035. Min Act: -0.0000

Data Index: 1612509 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1620872 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1563350 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7791. Min Act: 0.0000

Data Index: 1500111 (Python Code)

Max Activating Token Index: 995

Text #6

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1474983 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1432758 (Python Code)

Max Activating Token Index: 348

Text #8

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1445952 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1634020 (Python Code)

Max Activating Token Index: 499

Text #10

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1645878 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1610815 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1446922 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1505757 (Python Code)

Max Activating Token Index: 312

Text #14

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1409214 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.6864. Min Act: 0.0000

Data Index: 1381835 (Python Code)

Max Activating Token Index: 349

Text #16

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1487439 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1540709 (Python Code)

Max Activating Token Index: 933

Text #18

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1540600 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1420456 (Python Code)

Max Activating Token Index: 381