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

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

Neuron 6082 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: 4.7512. Min Range: -4.7512

Max Act: 4.6363. Min Act: -0.0000

Data Index: 719654 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.6441. Min Act: -0.0000

Data Index: 548719 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.7512. Min Act: -0.0000

Data Index: 266210 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.5481. Min Act: -0.0000

Data Index: 1041908 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.5515. Min Act: -0.0000

Data Index: 158809 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.1899. Min Act: -0.0000

Data Index: 360361 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.3065. Min Act: -0.0000

Data Index: 1267140 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.2683. Min Act: -0.0000

Data Index: 1273248 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.5991. Min Act: -0.0000

Data Index: 803362 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.2331. Min Act: -0.0000

Data Index: 476277 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.1911. Min Act: -0.0000

Data Index: 743288 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.2040. Min Act: -0.0000

Data Index: 754581 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.2586. Min Act: -0.0000

Data Index: 1394644 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.2471. Min Act: -0.0000

Data Index: 1538974 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.2171. Min Act: -0.0000

Data Index: 181447 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.1954. Min Act: -0.0000

Data Index: 217051 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.1873. Min Act: -0.0000

Data Index: 96499 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.1618. Min Act: -0.0000

Data Index: 863417 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.1443. Min Act: -0.0000

Data Index: 1374599 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 4.7512. Min Range: -4.7512

Max Act: 4.0957. Min Act: -0.0000

Data Index: 103878 (C4 (Web Text))

Max Activating Token Index: 647