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

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

Neuron 3643 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: 5.9007. Min Range: -5.9007

Max Act: 5.9007. Min Act: -0.0000

Data Index: 542540 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 5.9007. Min Range: -5.9007

Max Act: 5.4872. Min Act: -0.0000

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.9007. Min Range: -5.9007

Max Act: 5.4428. Min Act: -0.0000

Data Index: 1251648 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 5.9007. Min Range: -5.9007

Max Act: 5.2449. Min Act: -0.0000

Data Index: 1292491 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 5.9007. Min Range: -5.9007

Max Act: 5.2880. Min Act: -0.0000

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 5.9007. Min Range: -5.9007

Max Act: 5.1130. Min Act: -0.0000

Data Index: 539883 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 5.9007. Min Range: -5.9007

Max Act: 5.1192. Min Act: -0.0000

Data Index: 1337160 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.6030. Min Act: -0.0001

Data Index: 458792 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 5.9007. Min Range: -5.9007

Max Act: 5.0709. Min Act: -0.0000

Data Index: 450643 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.6796. Min Act: -0.0000

Data Index: 23818 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.7657. Min Act: -0.0000

Data Index: 1308278 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.3793. Min Act: -0.0001

Data Index: 587853 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.4285. Min Act: -0.0001

Data Index: 638964 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.7915. Min Act: -0.0000

Data Index: 758779 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.6061. Min Act: -0.0001

Data Index: 1253462 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.3761. Min Act: -0.0000

Data Index: 1085125 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.6881. Min Act: -0.0000

Data Index: 76202 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.3121. Min Act: -0.0000

Data Index: 757253 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.7864. Min Act: -0.0000

Data Index: 427875 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 5.9007. Min Range: -5.9007

Max Act: 4.5481. Min Act: -0.0000

Data Index: 676217 (C4 (Web Text))

Max Activating Token Index: 651