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

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

Neuron 65 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0000

Data Index: 96993 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0837. Min Act: -0.0000

Data Index: 531719 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0825. Min Act: -0.0000

Data Index: 49500 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1158015 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0727. Min Act: -0.0000

Data Index: 419350 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0747. Min Act: -0.0000

Data Index: 718282 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0709. Min Act: -0.0000

Data Index: 175394 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0708. Min Act: -0.0000

Data Index: 345317 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1340986 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0705. Min Act: -0.0000

Data Index: 713665 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0706. Min Act: -0.0000

Data Index: 139475 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0689. Min Act: -0.0000

Data Index: 626590 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0690. Min Act: -0.0000

Data Index: 320029 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0668. Min Act: -0.0000

Data Index: 557597 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0666. Min Act: -0.0000

Data Index: 606138 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1117621 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1071835 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0675. Min Act: -0.0000

Data Index: 754767 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1046718 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1302620 (C4 (Web Text))

Max Activating Token Index: 634