Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2648 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.2013. Min Act: -0.0000

Data Index: 935904 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.2964. Min Act: -0.0000

Data Index: 883669 (The Pile)

Max Activating Token Index: 483

Text #2

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.1461. Min Act: -0.0000

Data Index: 1705396 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.0808. Min Act: -0.0000

Data Index: 1166788 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.2198. Min Act: -0.0000

Data Index: 1023926 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.3456. Min Act: -0.0000

Data Index: 1332154 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.1990. Min Act: -0.0000

Data Index: 330623 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.1509. Min Act: -0.0000

Data Index: 580104 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.1132. Min Act: -0.0000

Data Index: 1506351 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.1037. Min Act: -0.0000

Data Index: 1718778 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.1042. Min Act: -0.0000

Data Index: 465138 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.2190. Min Act: -0.0000

Data Index: 872371 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 3.3456. Min Range: -3.3456

Max Act: 2.9089. Min Act: -0.0000

Data Index: 1260503 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 3.3456. Min Range: -3.3456

Max Act: 2.8717. Min Act: -0.0000

Data Index: 735585 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 3.3456. Min Range: -3.3456

Max Act: 2.8556. Min Act: -0.0000

Data Index: 684203 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 3.3456. Min Range: -3.3456

Max Act: 3.1083. Min Act: -0.0000

Data Index: 693232 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 3.3456. Min Range: -3.3456

Max Act: 2.8277. Min Act: -0.0000

Data Index: 259552 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 3.3456. Min Range: -3.3456

Max Act: 2.9703. Min Act: -0.0000

Data Index: 1531234 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 3.3456. Min Range: -3.3456

Max Act: 2.8256. Min Act: -0.0000

Data Index: 1877601 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 3.3456. Min Range: -3.3456

Max Act: 2.9484. Min Act: -0.0000

Data Index: 350883 (The Pile)

Max Activating Token Index: 710