Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1518 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0003

Data Index: 183426 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1441749 (Python Code)

Max Activating Token Index: 718

Text #2

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 122932 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1559145 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 383078 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0004

Data Index: 409704 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 810912 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 976231 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1646399 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1513612 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 927931 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1411298 (Python Code)

Max Activating Token Index: 283

Text #12

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 544842 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1527384 (Python Code)

Max Activating Token Index: 210

Text #14

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1191081 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1475607 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 547035 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1180511 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 792860 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1596847 (Python Code)

Max Activating Token Index: 57