Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1196 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3402. Min Range: -2.3402

Max Act: 2.3402. Min Act: -0.0000

Data Index: 836117 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 2.3402. Min Range: -2.3402

Max Act: 2.2732. Min Act: -0.0000

Data Index: 790578 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.3402. Min Range: -2.3402

Max Act: 2.0738. Min Act: -0.0000

Data Index: 804003 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1057240 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 2.3402. Min Range: -2.3402

Max Act: 2.0621. Min Act: -0.0000

Data Index: 686347 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.3402. Min Range: -2.3402

Max Act: 2.0024. Min Act: -0.0000

Data Index: 716798 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.8049. Min Act: -0.0000

Data Index: 829165 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.8090. Min Act: -0.0000

Data Index: 305161 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.8489. Min Act: -0.0001

Data Index: 409694 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.8799. Min Act: -0.0001

Data Index: 5187 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.8763. Min Act: -0.0000

Data Index: 613063 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.7942. Min Act: -0.0000

Data Index: 1266865 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.7502. Min Act: -0.0000

Data Index: 995553 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.8330. Min Act: -0.0000

Data Index: 219547 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.7568. Min Act: -0.0000

Data Index: 1296756 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.7630. Min Act: -0.0000

Data Index: 448561 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.6544. Min Act: -0.0000

Data Index: 818348 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.7276. Min Act: -0.0001

Data Index: 575478 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.7366. Min Act: -0.0000

Data Index: 531550 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 2.3402. Min Range: -2.3402

Max Act: 1.5824. Min Act: -0.0001

Data Index: 404123 (C4 (Web Text))

Max Activating Token Index: 727