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

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

Neuron 276 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4541. Min Act: -0.0000

Data Index: 716201 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4141. Min Act: -0.0000

Data Index: 509401 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4088. Min Act: -0.0000

Data Index: 995728 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3924. Min Act: -0.0000

Data Index: 926307 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4339. Min Act: -0.0000

Data Index: 245864 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4021. Min Act: -0.0000

Data Index: 42731 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3797. Min Act: -0.0000

Data Index: 570978 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3778. Min Act: -0.0000

Data Index: 259204 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1355084 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1211877 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3791. Min Act: -0.0000

Data Index: 898125 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3658. Min Act: -0.0000

Data Index: 788779 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3608. Min Act: -0.0000

Data Index: 349367 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3610. Min Act: -0.0000

Data Index: 951785 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3404. Min Act: -0.0000

Data Index: 250950 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3508. Min Act: -0.0000

Data Index: 897097 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1131916 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3360. Min Act: -0.0000

Data Index: 556932 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3688. Min Act: -0.0000

Data Index: 300108 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3540. Min Act: -0.0000

Data Index: 854330 (C4 (Web Text))

Max Activating Token Index: 889