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

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

Neuron 510 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2683. Min Range: -3.2683

Max Act: 3.0000. Min Act: -0.0000

Data Index: 933747 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 3.2683. Min Range: -3.2683

Max Act: 3.1279. Min Act: -0.0000

Data Index: 996341 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 3.2683. Min Range: -3.2683

Max Act: 3.2683. Min Act: -0.0000

Data Index: 147558 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 3.2683. Min Range: -3.2683

Max Act: 3.2380. Min Act: -0.0000

Data Index: 393051 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 3.2683. Min Range: -3.2683

Max Act: 3.0909. Min Act: -0.0000

Data Index: 87402 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.2683. Min Range: -3.2683

Max Act: 3.0047. Min Act: -0.0000

Data Index: 714871 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.9574. Min Act: -0.0000

Data Index: 790057 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.9091. Min Act: -0.0000

Data Index: 321 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 3.2683. Min Range: -3.2683

Max Act: 3.0420. Min Act: -0.0000

Data Index: 458702 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.9962. Min Act: -0.0000

Data Index: 719496 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.8506. Min Act: -0.0000

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.9778. Min Act: -0.0000

Data Index: 922068 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.8442. Min Act: -0.0000

Data Index: 1290169 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.9669. Min Act: -0.0000

Data Index: 722423 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.8363. Min Act: -0.0000

Data Index: 1255730 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.8164. Min Act: -0.0000

Data Index: 726465 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.8021. Min Act: -0.0000

Data Index: 921116 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.9524. Min Act: -0.0000

Data Index: 1206954 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.7912. Min Act: -0.0000

Data Index: 39971 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 3.2683. Min Range: -3.2683

Max Act: 2.7556. Min Act: -0.0000

Data Index: 287996 (C4 (Web Text))

Max Activating Token Index: 822