Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3739 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0201. Min Range: -4.0201

Max Act: 4.0201. Min Act: -0.0000

Data Index: 671247 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 4.0201. Min Range: -4.0201

Max Act: 3.7658. Min Act: -0.0000

Data Index: 192354 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 4.0201. Min Range: -4.0201

Max Act: 3.6885. Min Act: -0.0000

Data Index: 995175 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 4.0201. Min Range: -4.0201

Max Act: 3.4701. Min Act: -0.0000

Data Index: 657600 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 4.0201. Min Range: -4.0201

Max Act: 3.0312. Min Act: -0.0000

Data Index: 774995 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.9392. Min Act: -0.0000

Data Index: 527472 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 4.0201. Min Range: -4.0201

Max Act: 3.1400. Min Act: -0.0000

Data Index: 750722 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.8267. Min Act: -0.0000

Data Index: 131108 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 4.0201. Min Range: -4.0201

Max Act: 3.1858. Min Act: -0.0000

Data Index: 1198884 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.8838. Min Act: -0.0000

Data Index: 50152 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.7537. Min Act: -0.0000

Data Index: 56020 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.4739. Min Act: -0.0000

Data Index: 1112862 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.5774. Min Act: -0.0000

Data Index: 1013280 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.7580. Min Act: -0.0000

Data Index: 763659 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.7455. Min Act: -0.0000

Data Index: 358191 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.5558. Min Act: -0.0000

Data Index: 853896 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.3408. Min Act: -0.0000

Data Index: 1160372 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.5010. Min Act: -0.0000

Data Index: 853251 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.5304. Min Act: -0.0000

Data Index: 338040 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 4.0201. Min Range: -4.0201

Max Act: 2.4991. Min Act: -0.0000

Data Index: 1146943 (C4 (Web Text))

Max Activating Token Index: 649