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

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

Neuron 876 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: 2.1424. Min Range: -2.1424

Max Act: 2.1424. Min Act: -0.0000

Data Index: 415339 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 2.1424. Min Range: -2.1424

Max Act: 2.0431. Min Act: -0.0000

Data Index: 1305988 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 2.1424. Min Range: -2.1424

Max Act: 2.0472. Min Act: -0.0000

Data Index: 1458715 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.9794. Min Act: -0.0000

Data Index: 395150 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.8772. Min Act: -0.0000

Data Index: 516887 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.9474. Min Act: -0.0000

Data Index: 1243839 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.9211. Min Act: -0.0000

Data Index: 996823 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.8486. Min Act: -0.0000

Data Index: 203906 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.7987. Min Act: -0.0000

Data Index: 399013 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.7804. Min Act: -0.0000

Data Index: 176824 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.6501. Min Act: -0.0000

Data Index: 1367386 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.7409. Min Act: -0.0000

Data Index: 1398526 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.8576. Min Act: -0.0000

Data Index: 856684 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.6725. Min Act: -0.0000

Data Index: 1190014 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1087992 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.6792. Min Act: -0.0000

Data Index: 615480 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.6590. Min Act: -0.0000

Data Index: 1400092 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.6354. Min Act: -0.0000

Data Index: 1283406 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.7231. Min Act: -0.0000

Data Index: 1318972 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 2.1424. Min Range: -2.1424

Max Act: 1.6309. Min Act: -0.0000

Data Index: 1284957 (C4 (Web Text))

Max Activating Token Index: 662