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

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

Neuron 3867 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: 0.9500. Min Range: -0.9500

Max Act: 0.9500. Min Act: -0.0000

Data Index: 896872 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1152160 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8802. Min Act: -0.0000

Data Index: 182239 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8263. Min Act: -0.0001

Data Index: 315144 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8528. Min Act: -0.0001

Data Index: 887877 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1170066 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7939. Min Act: -0.0000

Data Index: 993236 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8129. Min Act: -0.0000

Data Index: 35864 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8090. Min Act: -0.0000

Data Index: 912073 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7706. Min Act: -0.0001

Data Index: 154273 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7906. Min Act: -0.0000

Data Index: 258528 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7894. Min Act: -0.0000

Data Index: 824479 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7593. Min Act: -0.0000

Data Index: 703724 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7587. Min Act: -0.0001

Data Index: 630630 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1147169 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7784. Min Act: -0.0000

Data Index: 861056 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7716. Min Act: -0.0000

Data Index: 358270 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1178798 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.8229. Min Act: -0.0001

Data Index: 96618 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.9500. Min Range: -0.9500

Max Act: 0.7965. Min Act: -0.0001

Data Index: 215093 (C4 (Web Text))

Max Activating Token Index: 381