Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1640563 (Python Code)

Max Activating Token Index: 949

Text #1

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1548258 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1575069 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1555856 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1640972 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1428618 (Python Code)

Max Activating Token Index: 156

Text #6

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1551194 (Python Code)

Max Activating Token Index: 587

Text #7

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1368352 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1625207 (Python Code)

Max Activating Token Index: 853

Text #9

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1530602 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1652858 (Python Code)

Max Activating Token Index: 603

Text #11

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1512215 (Python Code)

Max Activating Token Index: 1002

Text #12

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1504486 (Python Code)

Max Activating Token Index: 730

Text #13

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1506154 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1544932 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1419518 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1598505 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1394537 (Python Code)

Max Activating Token Index: 137

Text #18

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1475160 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1485137 (Python Code)

Max Activating Token Index: 60