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

Dataset: The Pile

Neuron 800 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.5547. Min Act: -0.0000

Data Index: 1939644 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.4511. Min Act: -0.0000

Data Index: 872424 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1558408 (The Pile)

Max Activating Token Index: 203

Text #3

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3566. Min Act: -0.0000

Data Index: 760048 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1307706 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1819062 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1963668 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2549. Min Act: -0.0000

Data Index: 253404 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3192. Min Act: -0.0000

Data Index: 54338 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1743500 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3591. Min Act: -0.0000

Data Index: 736498 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1832508 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1267359 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1920422 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2673. Min Act: -0.0000

Data Index: 526879 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1189820 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1090671 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1781. Min Act: -0.0000

Data Index: 114820 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1615. Min Act: -0.0000

Data Index: 448099 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1874719 (The Pile)

Max Activating Token Index: 227