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

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

Neuron 4256 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.9758. Min Act: -0.0000

Data Index: 1596971 (Python Code)

Max Activating Token Index: 1019

Text #1

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6360. Min Act: -0.0000

Data Index: 1419196 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6966. Min Act: -0.0000

Data Index: 1420454 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6127. Min Act: -0.0001

Data Index: 13049 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1215151 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5927. Min Act: -0.0000

Data Index: 461559 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.4728. Min Act: -0.0000

Data Index: 393688 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.4360. Min Act: -0.0000

Data Index: 51888 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1498990 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5800. Min Act: -0.0001

Data Index: 935503 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5490. Min Act: -0.0001

Data Index: 460071 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1493207 (Python Code)

Max Activating Token Index: 887

Text #12

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.3762. Min Act: -0.0000

Data Index: 1571275 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.3311. Min Act: -0.0001

Data Index: 231804 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.5168. Min Act: -0.0000

Data Index: 841650 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.2922. Min Act: -0.0001

Data Index: 1461706 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.3229. Min Act: -0.0000

Data Index: 470795 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1396403 (Python Code)

Max Activating Token Index: 997

Text #18

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1410175 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 1.9758. Min Range: -1.9758

Max Act: 1.3846. Min Act: -0.0001

Data Index: 13101 (C4 (Web Text))

Max Activating Token Index: 648