Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0673. Min Act: -0.0001

Data Index: 829298 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0637. Min Act: -0.0001

Data Index: 27931 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0589. Min Act: -0.0001

Data Index: 52686 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0530. Min Act: -0.0001

Data Index: 956157 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0643. Min Act: -0.0001

Data Index: 628414 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0606. Min Act: -0.0001

Data Index: 50873 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0582. Min Act: -0.0001

Data Index: 744933 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0638. Min Act: -0.0001

Data Index: 684959 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1193811 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0544. Min Act: -0.0001

Data Index: 957479 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0563. Min Act: -0.0001

Data Index: 773898 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0527. Min Act: -0.0001

Data Index: 754952 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1300464 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1610579 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1263693 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0535. Min Act: -0.0001

Data Index: 900737 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0585. Min Act: -0.0001

Data Index: 959924 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0521. Min Act: -0.0001

Data Index: 841781 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0589. Min Act: -0.0001

Data Index: 418616 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1328218 (C4 (Web Text))

Max Activating Token Index: 527