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

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

Neuron 869 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: 2.5933. Min Range: -2.5933

Max Act: 2.5933. Min Act: -0.0000

Data Index: 1559482 (Python Code)

Max Activating Token Index: 877

Text #1

Max Range: 2.5933. Min Range: -2.5933

Max Act: 2.0173. Min Act: -0.0000

Data Index: 694673 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 2.5933. Min Range: -2.5933

Max Act: 2.0964. Min Act: -0.0000

Data Index: 1415280 (Python Code)

Max Activating Token Index: 480

Text #3

Max Range: 2.5933. Min Range: -2.5933

Max Act: 2.0684. Min Act: -0.0000

Data Index: 351881 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 2.5933. Min Range: -2.5933

Max Act: 2.1592. Min Act: -0.0000

Data Index: 1344975 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1619705 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.9042. Min Act: -0.0000

Data Index: 1494741 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.8664. Min Act: -0.0000

Data Index: 263933 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.9603. Min Act: -0.0000

Data Index: 617757 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.7343. Min Act: -0.0000

Data Index: 1496381 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.8144. Min Act: -0.0000

Data Index: 1483665 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.6789. Min Act: -0.0000

Data Index: 1430027 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.8848. Min Act: -0.0000

Data Index: 1548581 (Python Code)

Max Activating Token Index: 523

Text #13

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.8725. Min Act: -0.0000

Data Index: 1490926 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.7671. Min Act: -0.0000

Data Index: 1553849 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.7672. Min Act: -0.0000

Data Index: 1386769 (Python Code)

Max Activating Token Index: 568

Text #16

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1498672 (Python Code)

Max Activating Token Index: 802

Text #17

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1624594 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.7876. Min Act: -0.0000

Data Index: 1520076 (Python Code)

Max Activating Token Index: 263

Text #19

Max Range: 2.5933. Min Range: -2.5933

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1653659 (Python Code)

Max Activating Token Index: 5