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

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

Neuron 1616 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.6763. Min Act: -0.0000

Data Index: 772260 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.3496. Min Act: -0.0000

Data Index: 754619 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1331780 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.3437. Min Act: -0.0000

Data Index: 468819 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.0947. Min Act: -0.0000

Data Index: 277571 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.0477. Min Act: -0.0001

Data Index: 134498 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1352490 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.0430. Min Act: -0.0000

Data Index: 573032 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.0080. Min Act: -0.0000

Data Index: 198341 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1151185 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.6763. Min Range: -1.6763

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1177663 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.8415. Min Act: -0.0001

Data Index: 1317761 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9030. Min Act: -0.0000

Data Index: 117235 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9608. Min Act: -0.0000

Data Index: 478113 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9658. Min Act: -0.0000

Data Index: 802898 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9092. Min Act: -0.0000

Data Index: 821406 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.9423. Min Act: -0.0000

Data Index: 28389 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1408763 (Python Code)

Max Activating Token Index: 309

Text #18

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1295495 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.6763. Min Range: -1.6763

Max Act: 0.8483. Min Act: -0.0000

Data Index: 362106 (C4 (Web Text))

Max Activating Token Index: 823