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

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

Neuron 688 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7660. Min Act: -0.0001

Data Index: 898886 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7677. Min Act: -0.0001

Data Index: 344644 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7706. Min Act: -0.0001

Data Index: 672324 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7705. Min Act: -0.0001

Data Index: 313573 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7239. Min Act: -0.0001

Data Index: 960466 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7371. Min Act: -0.0001

Data Index: 996654 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7182. Min Act: -0.0001

Data Index: 233541 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.7077. Min Act: -0.0001

Data Index: 466236 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6748. Min Act: -0.0001

Data Index: 995261 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6901. Min Act: -0.0001

Data Index: 1178756 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6281. Min Act: -0.0001

Data Index: 123761 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6219. Min Act: -0.0001

Data Index: 434398 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1039728 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6190. Min Act: -0.0001

Data Index: 513548 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6300. Min Act: -0.0001

Data Index: 1290852 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6225. Min Act: -0.0001

Data Index: 976091 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6178. Min Act: -0.0001

Data Index: 636921 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.6201. Min Act: -0.0001

Data Index: 398783 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.5774. Min Act: -0.0001

Data Index: 48047 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.7706. Min Range: -0.7706

Max Act: 0.5939. Min Act: -0.0001

Data Index: 137232 (C4 (Web Text))

Max Activating Token Index: 227