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

Dataset: The Pile

Neuron 32 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1754400 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1469726 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1512600 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4285. Min Act: -0.0000

Data Index: 59399 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1509809 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4123. Min Act: -0.0000

Data Index: 229058 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4077. Min Act: -0.0000

Data Index: 62626 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4071. Min Act: -0.0000

Data Index: 784480 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1503193 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3927. Min Act: -0.0000

Data Index: 474493 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1041182 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1753675 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1425404 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1223092 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3688. Min Act: -0.0000

Data Index: 481362 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3514. Min Act: -0.0000

Data Index: 349489 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1611710 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1567608 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1033847 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1201716 (The Pile)

Max Activating Token Index: 148