Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1852 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3936. Min Act: -0.0000

Data Index: 352639 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.4123. Min Act: -0.0000

Data Index: 814238 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1518264 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1514400 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.3154. Min Act: -0.0000

Data Index: 164253 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2784. Min Act: -0.0000

Data Index: 812316 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1933055 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2803. Min Act: -0.0000

Data Index: 253937 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1577532 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1671384 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2828. Min Act: -0.0000

Data Index: 25306 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2748. Min Act: -0.0000

Data Index: 903427 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2738. Min Act: -0.0000

Data Index: 802892 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2826. Min Act: -0.0000

Data Index: 980471 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2613. Min Act: -0.0000

Data Index: 756358 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2683. Min Act: -0.0000

Data Index: 96572 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1311862 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1298185 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1470840 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 0.4123. Min Range: -0.4123

Max Act: 0.2595. Min Act: -0.0000

Data Index: 480096 (The Pile)

Max Activating Token Index: 990