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

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

Neuron 371 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: 1.1209. Min Range: -1.1209

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1372110 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1605602 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1382851 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1389172 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1376016 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1505245 (Python Code)

Max Activating Token Index: 815

Text #6

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1562135 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1459259 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1512237 (Python Code)

Max Activating Token Index: 120

Text #9

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1506984 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1478914 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1614336 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1478462 (Python Code)

Max Activating Token Index: 340

Text #13

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1589999 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1576675 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1473433 (Python Code)

Max Activating Token Index: 658

Text #16

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1641578 (Python Code)

Max Activating Token Index: 892

Text #17

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1369511 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1004908 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1471716 (Python Code)

Max Activating Token Index: 682