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

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

Neuron 824 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.7269. Min Act: -0.0000

Data Index: 833079 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.3524. Min Act: -0.0000

Data Index: 507089 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.2617. Min Act: -0.0000

Data Index: 12827 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.2478. Min Act: -0.0000

Data Index: 673549 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.2429. Min Act: -0.0000

Data Index: 1190222 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.1827. Min Act: -0.0000

Data Index: 83846 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.0595. Min Act: -0.0000

Data Index: 824836 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.0867. Min Act: -0.0000

Data Index: 1283842 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.0011. Min Act: -0.0000

Data Index: 803684 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.8304. Min Act: 0.0000

Data Index: 1076257 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 2.7269. Min Range: -2.7269

Max Act: 2.0454. Min Act: -0.0000

Data Index: 476505 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.9190. Min Act: -0.0000

Data Index: 381315 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.9096. Min Act: -0.0000

Data Index: 132316 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1238601 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.8240. Min Act: -0.0000

Data Index: 874440 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.7020. Min Act: -0.0000

Data Index: 358017 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.8723. Min Act: -0.0000

Data Index: 644291 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.6716. Min Act: -0.0000

Data Index: 102504 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.7443. Min Act: -0.0000

Data Index: 18316 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.7269. Min Range: -2.7269

Max Act: 1.7022. Min Act: 0.0000

Data Index: 917528 (C4 (Web Text))

Max Activating Token Index: 672