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

Dataset: The Pile

Neuron 3055 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0000

Data Index: 631978 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7643. Min Act: -0.0000

Data Index: 787310 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1638636 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1648455 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7597. Min Act: -0.0000

Data Index: 321089 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8063. Min Act: -0.0000

Data Index: 888295 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1182184 (The Pile)

Max Activating Token Index: 59

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1562827 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7096. Min Act: -0.0000

Data Index: 912815 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6864. Min Act: -0.0000

Data Index: 796386 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1830058 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7331. Min Act: -0.0000

Data Index: 393102 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6954. Min Act: -0.0000

Data Index: 405559 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6980. Min Act: -0.0000

Data Index: 796583 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1028073 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6079. Min Act: -0.0000

Data Index: 117334 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1639341 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6443. Min Act: -0.0000

Data Index: 577316 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6835. Min Act: -0.0000

Data Index: 784098 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1003576 (The Pile)

Max Activating Token Index: 859