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

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

Neuron 3835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5907. Min Act: -0.0000

Data Index: 353605 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5697. Min Act: -0.0000

Data Index: 975220 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1120851 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5140. Min Act: -0.0000

Data Index: 561609 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1176406 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1273463 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4816. Min Act: -0.0000

Data Index: 776933 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4557. Min Act: -0.0000

Data Index: 257487 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4996. Min Act: -0.0000

Data Index: 617478 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1335180 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1017743 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1231859 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4613. Min Act: -0.0000

Data Index: 36168 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4491. Min Act: -0.0000

Data Index: 839181 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1330501 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4326. Min Act: -0.0000

Data Index: 482690 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4426. Min Act: -0.0000

Data Index: 781995 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4758. Min Act: -0.0000

Data Index: 921464 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4266. Min Act: -0.0000

Data Index: 113939 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1136914 (C4 (Web Text))

Max Activating Token Index: 601