Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1185 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9880. Min Act: -0.0001

Data Index: 1333460 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8128. Min Act: -0.0001

Data Index: 70144 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9024. Min Act: -0.0001

Data Index: 581585 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8494. Min Act: -0.0001

Data Index: 790728 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8240. Min Act: -0.0001

Data Index: 329758 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7402. Min Act: -0.0001

Data Index: 515403 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7883. Min Act: -0.0001

Data Index: 536629 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7044. Min Act: -0.0001

Data Index: 212745 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1230234 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6955. Min Act: -0.0001

Data Index: 961901 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6980. Min Act: -0.0001

Data Index: 603795 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6903. Min Act: -0.0001

Data Index: 599380 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6844. Min Act: -0.0001

Data Index: 290172 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6780. Min Act: -0.0001

Data Index: 277382 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6998. Min Act: -0.0001

Data Index: 433297 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6687. Min Act: -0.0001

Data Index: 190990 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7111. Min Act: -0.0001

Data Index: 782001 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7085. Min Act: -0.0001

Data Index: 1191416 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6805. Min Act: -0.0001

Data Index: 688893 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6690. Min Act: -0.0001

Data Index: 1250081 (C4 (Web Text))

Max Activating Token Index: 685