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

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

Neuron 4094 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.5452. Min Act: -0.0000

Data Index: 474035 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.3695. Min Act: -0.0000

Data Index: 61965 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.2682. Min Act: -0.0000

Data Index: 594010 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.2130. Min Act: -0.0000

Data Index: 95409 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1203486 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1896. Min Act: -0.0000

Data Index: 766002 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1730. Min Act: -0.0001

Data Index: 919619 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1676. Min Act: -0.0000

Data Index: 622755 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1998. Min Act: -0.0000

Data Index: 758583 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0646. Min Act: -0.0001

Data Index: 250578 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1121. Min Act: -0.0001

Data Index: 43968 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0799. Min Act: -0.0000

Data Index: 446971 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1000. Min Act: -0.0000

Data Index: 454459 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0595. Min Act: -0.0001

Data Index: 690419 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0127. Min Act: -0.0000

Data Index: 200250 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.1105. Min Act: -0.0000

Data Index: 720315 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0086. Min Act: -0.0000

Data Index: 181320 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.5452. Min Range: -1.5452

Max Act: 1.0048. Min Act: -0.0000

Data Index: 770138 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9802. Min Act: -0.0000

Data Index: 974653 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.5452. Min Range: -1.5452

Max Act: 0.9790. Min Act: -0.0000

Data Index: 810280 (C4 (Web Text))

Max Activating Token Index: 759