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

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

Neuron 535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0001

Data Index: 369840 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0545. Min Act: -0.0001

Data Index: 806241 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0489. Min Act: -0.0001

Data Index: 166752 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0536. Min Act: -0.0001

Data Index: 374704 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0480. Min Act: -0.0001

Data Index: 970835 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1295345 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0431. Min Act: -0.0001

Data Index: 749254 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0422. Min Act: -0.0001

Data Index: 612321 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0424. Min Act: -0.0001

Data Index: 35364 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0427. Min Act: -0.0001

Data Index: 589757 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0443. Min Act: -0.0001

Data Index: 867433 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0462. Min Act: -0.0001

Data Index: 651367 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0443. Min Act: -0.0001

Data Index: 279114 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1210231 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0449. Min Act: -0.0001

Data Index: 116890 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0437. Min Act: -0.0001

Data Index: 321764 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0452. Min Act: -0.0001

Data Index: 241150 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1097792 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1257366 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0387. Min Act: -0.0001

Data Index: 116946 (C4 (Web Text))

Max Activating Token Index: 203