Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4773. Min Act: -0.0001

Data Index: 184584 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4960. Min Act: -0.0001

Data Index: 1329182 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4854. Min Act: -0.0001

Data Index: 717452 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4690. Min Act: -0.0001

Data Index: 707635 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4848. Min Act: -0.0001

Data Index: 25005 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4775. Min Act: -0.0001

Data Index: 449805 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3972. Min Act: -0.0001

Data Index: 753487 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4268. Min Act: -0.0001

Data Index: 512683 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4549. Min Act: -0.0001

Data Index: 9884 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4521. Min Act: -0.0001

Data Index: 1051272 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4471. Min Act: -0.0001

Data Index: 867788 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4600. Min Act: -0.0001

Data Index: 1249931 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4564. Min Act: -0.0001

Data Index: 1262228 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4355. Min Act: -0.0001

Data Index: 54380 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4239. Min Act: -0.0001

Data Index: 327235 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4247. Min Act: -0.0001

Data Index: 787599 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3933. Min Act: -0.0001

Data Index: 835476 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4076. Min Act: -0.0001

Data Index: 644411 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4063. Min Act: -0.0001

Data Index: 328656 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1255309 (C4 (Web Text))

Max Activating Token Index: 859