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

Dataset: The Pile

Neuron 618 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.5211. Min Act: -0.0000

Data Index: 1917096 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1751. Min Act: -0.0000

Data Index: 994306 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1840415 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.2883. Min Act: -0.0000

Data Index: 658842 (The Pile)

Max Activating Token Index: 470

Text #4

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1051105 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1134909 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1327. Min Act: -0.0000

Data Index: 592015 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1200. Min Act: -0.0000

Data Index: 188689 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9847. Min Act: -0.0000

Data Index: 111554 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0652. Min Act: -0.0000

Data Index: 147655 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1661087 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1740053 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1454756 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0320. Min Act: -0.0000

Data Index: 262377 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0666. Min Act: -0.0000

Data Index: 452490 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9355. Min Act: -0.0000

Data Index: 119945 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1519021 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9946. Min Act: -0.0000

Data Index: 98292 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1918166 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1484254 (The Pile)

Max Activating Token Index: 574