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

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

Neuron 407 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: 0.9690. Min Range: -0.9690

Max Act: 0.9099. Min Act: -0.0001

Data Index: 786022 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9133. Min Act: -0.0001

Data Index: 299373 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9682. Min Act: -0.0001

Data Index: 686580 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1017786 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9137. Min Act: -0.0001

Data Index: 1265870 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9326. Min Act: -0.0001

Data Index: 659038 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.8314. Min Act: -0.0001

Data Index: 336158 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.8610. Min Act: -0.0001

Data Index: 568830 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.8466. Min Act: -0.0001

Data Index: 634 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.8075. Min Act: -0.0001

Data Index: 659306 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.8243. Min Act: -0.0001

Data Index: 64993 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.8148. Min Act: -0.0001

Data Index: 620795 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7746. Min Act: -0.0001

Data Index: 679576 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7923. Min Act: -0.0001

Data Index: 132087 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7944. Min Act: -0.0001

Data Index: 303269 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7819. Min Act: -0.0001

Data Index: 499923 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7229. Min Act: -0.0001

Data Index: 1238207 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7809. Min Act: -0.0001

Data Index: 4750 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7296. Min Act: -0.0001

Data Index: 1226907 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7951. Min Act: -0.0001

Data Index: 310350 (C4 (Web Text))

Max Activating Token Index: 919