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

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

Neuron 3034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.7456. Min Act: -0.0000

Data Index: 858643 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6853. Min Act: -0.0000

Data Index: 263378 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6651. Min Act: -0.0001

Data Index: 913313 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6506. Min Act: -0.0001

Data Index: 996356 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6818. Min Act: -0.0000

Data Index: 379710 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6467. Min Act: -0.0000

Data Index: 835999 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6482. Min Act: -0.0001

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1132626 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6469. Min Act: -0.0000

Data Index: 479685 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6260. Min Act: -0.0000

Data Index: 192708 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6609. Min Act: -0.0000

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6009. Min Act: -0.0001

Data Index: 484781 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6570. Min Act: -0.0001

Data Index: 1083819 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6382. Min Act: -0.0000

Data Index: 537285 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.5952. Min Act: -0.0000

Data Index: 109907 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6217. Min Act: -0.0000

Data Index: 715074 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6244. Min Act: -0.0000

Data Index: 303565 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.5767. Min Act: -0.0001

Data Index: 277024 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.5992. Min Act: -0.0001

Data Index: 230605 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.6267. Min Act: -0.0001

Data Index: 1354535 (C4 (Web Text))

Max Activating Token Index: 574