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

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

Neuron 2750 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.6673. Min Act: -0.0000

Data Index: 391322 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.5882. Min Act: -0.0000

Data Index: 899591 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.6355. Min Act: -0.0000

Data Index: 818336 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.5208. Min Act: -0.0000

Data Index: 721780 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.4840. Min Act: -0.0000

Data Index: 724503 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1154920 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3698. Min Act: -0.0000

Data Index: 1477784 (Python Code)

Max Activating Token Index: 785

Text #7

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3946. Min Act: -0.0000

Data Index: 3414 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1250292 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3791. Min Act: -0.0000

Data Index: 828716 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3662. Min Act: -0.0000

Data Index: 411786 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1412922 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.4304. Min Act: -0.0000

Data Index: 885699 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3303. Min Act: -0.0000

Data Index: 109942 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3101. Min Act: -0.0000

Data Index: 372692 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.2871. Min Act: -0.0000

Data Index: 613468 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1171920 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.3545. Min Act: -0.0000

Data Index: 399927 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.2843. Min Act: -0.0000

Data Index: 885326 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.6673. Min Range: -1.6673

Max Act: 1.2729. Min Act: -0.0000

Data Index: 521231 (C4 (Web Text))

Max Activating Token Index: 188