Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4925 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.8605. Min Act: -0.0000

Data Index: 736640 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.8804. Min Act: -0.0000

Data Index: 611928 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.8364. Min Act: -0.0000

Data Index: 426953 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.8390. Min Act: -0.0000

Data Index: 885188 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1242450 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7668. Min Act: -0.0000

Data Index: 733727 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.8317. Min Act: -0.0001

Data Index: 145773 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7813. Min Act: -0.0000

Data Index: 22828 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.8206. Min Act: -0.0000

Data Index: 700280 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7646. Min Act: -0.0000

Data Index: 583240 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1150040 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1263465 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1231785 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1953 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7456. Min Act: -0.0000

Data Index: 962146 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.6949. Min Act: -0.0000

Data Index: 464181 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7290. Min Act: -0.0000

Data Index: 269217 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7047. Min Act: -0.0000

Data Index: 270220 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1141619 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.8804. Min Range: -0.8804

Max Act: 0.6816. Min Act: -0.0000

Data Index: 75978 (C4 (Web Text))

Max Activating Token Index: 1022