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

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

Neuron 5458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4630. Min Range: -4.4630

Max Act: 4.4630. Min Act: -0.0000

Data Index: 1585647 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.8414. Min Act: -0.0000

Data Index: 1611980 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.9076. Min Act: -0.0000

Data Index: 1577340 (Python Code)

Max Activating Token Index: 684

Text #3

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.7732. Min Act: -0.0000

Data Index: 1654321 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.5057. Min Act: -0.0000

Data Index: 1596929 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.5235. Min Act: -0.0000

Data Index: 1403630 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.4840. Min Act: -0.0000

Data Index: 1518529 (Python Code)

Max Activating Token Index: 588

Text #7

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.4854. Min Act: -0.0000

Data Index: 1573946 (Python Code)

Max Activating Token Index: 280

Text #8

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.3805. Min Act: -0.0000

Data Index: 1544061 (Python Code)

Max Activating Token Index: 965

Text #9

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.3559. Min Act: -0.0000

Data Index: 1366450 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.3597. Min Act: -0.0000

Data Index: 1514353 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.3295. Min Act: -0.0000

Data Index: 1486076 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.1905. Min Act: -0.0000

Data Index: 1414208 (Python Code)

Max Activating Token Index: 1008

Text #13

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.4720. Min Act: -0.0000

Data Index: 1520811 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.3045. Min Act: -0.0000

Data Index: 1639271 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.4377. Min Act: -0.0000

Data Index: 1458111 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.4059. Min Act: -0.0000

Data Index: 1427020 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.0988. Min Act: -0.0000

Data Index: 1591981 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.3884. Min Act: -0.0000

Data Index: 1540923 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 4.4630. Min Range: -4.4630

Max Act: 3.0874. Min Act: -0.0000

Data Index: 1521638 (Python Code)

Max Activating Token Index: 554