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

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

Neuron 4746 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0627. Min Act: -0.0002

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0611. Min Act: -0.0002

Data Index: 250241 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0535. Min Act: -0.0002

Data Index: 501157 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0533. Min Act: -0.0002

Data Index: 927196 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0519. Min Act: -0.0002

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1224390 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0485. Min Act: -0.0002

Data Index: 383955 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1080842 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0491. Min Act: -0.0002

Data Index: 136843 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1038908 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0470. Min Act: -0.0002

Data Index: 168782 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0436. Min Act: -0.0002

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1286595 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1087140 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0428. Min Act: -0.0002

Data Index: 549132 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1292692 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0427. Min Act: -0.0002

Data Index: 57668 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1173865 (C4 (Web Text))

Max Activating Token Index: 159