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

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

Neuron 2653 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: 0.5620. Min Range: -0.5620

Max Act: 0.5620. Min Act: -0.0001

Data Index: 977644 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4943. Min Act: -0.0001

Data Index: 218047 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4685. Min Act: -0.0001

Data Index: 290132 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.5129. Min Act: -0.0001

Data Index: 1231999 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4479. Min Act: -0.0001

Data Index: 1224703 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4771. Min Act: -0.0001

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4890. Min Act: -0.0001

Data Index: 512348 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4985. Min Act: -0.0001

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4465. Min Act: -0.0001

Data Index: 87266 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4480. Min Act: -0.0001

Data Index: 289625 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4331. Min Act: -0.0001

Data Index: 222889 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4391. Min Act: -0.0001

Data Index: 963567 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4590. Min Act: -0.0001

Data Index: 1213427 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4478. Min Act: -0.0001

Data Index: 386437 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4108. Min Act: -0.0001

Data Index: 225152 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4532. Min Act: -0.0001

Data Index: 1043545 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4064. Min Act: -0.0001

Data Index: 473310 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4092. Min Act: -0.0000

Data Index: 510018 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.3855. Min Act: -0.0001

Data Index: 1296791 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4056. Min Act: -0.0001

Data Index: 216551 (C4 (Web Text))

Max Activating Token Index: 173