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

Dataset: The Pile

Neuron 3790 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9227. Min Range: -7.9227

Max Act: 7.9227. Min Act: -0.0000

Data Index: 1804433 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 7.9227. Min Range: -7.9227

Max Act: 4.8172. Min Act: -0.0000

Data Index: 991945 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 7.9227. Min Range: -7.9227

Max Act: 4.4454. Min Act: -0.0000

Data Index: 86459 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 7.9227. Min Range: -7.9227

Max Act: 4.5873. Min Act: -0.0000

Data Index: 526493 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.9211. Min Act: -0.0000

Data Index: 1488075 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.9266. Min Act: -0.0000

Data Index: 111923 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 7.9227. Min Range: -7.9227

Max Act: 4.1532. Min Act: -0.0000

Data Index: 1304290 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.9554. Min Act: 0.0000

Data Index: 914847 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.8108. Min Act: -0.0000

Data Index: 302168 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.8185. Min Act: -0.0000

Data Index: 583842 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.5568. Min Act: -0.0000

Data Index: 1361336 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.8274. Min Act: -0.0000

Data Index: 1870240 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.8153. Min Act: -0.0000

Data Index: 1091187 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 7.9227. Min Range: -7.9227

Max Act: 4.0812. Min Act: -0.0000

Data Index: 952860 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.3727. Min Act: -0.0000

Data Index: 1066548 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.3693. Min Act: 0.0000

Data Index: 975870 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.3689. Min Act: -0.0000

Data Index: 1562832 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.3728. Min Act: -0.0000

Data Index: 689588 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.4633. Min Act: 0.0000

Data Index: 1590747 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 7.9227. Min Range: -7.9227

Max Act: 3.5647. Min Act: -0.0000

Data Index: 1196248 (The Pile)

Max Activating Token Index: 844