Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3751 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.9717. Min Act: -0.0000

Data Index: 1053135 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7416. Min Act: -0.0000

Data Index: 480833 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8516. Min Act: -0.0000

Data Index: 311635 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7138. Min Act: -0.0000

Data Index: 76027 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.6549. Min Act: -0.0000

Data Index: 522757 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.6394. Min Act: -0.0000

Data Index: 493010 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.4394. Min Act: -0.0000

Data Index: 1313162 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.5180. Min Act: -0.0000

Data Index: 188570 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.5050. Min Act: -0.0000

Data Index: 390502 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.4975. Min Act: -0.0000

Data Index: 517378 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.4767. Min Act: -0.0000

Data Index: 700245 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.3096. Min Act: -0.0000

Data Index: 838831 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.2866. Min Act: -0.0000

Data Index: 819381 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.1563. Min Act: -0.0000

Data Index: 381534 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.4146. Min Act: -0.0000

Data Index: 1190725 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.2701. Min Act: -0.0000

Data Index: 259565 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.2665. Min Act: -0.0000

Data Index: 356590 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.3885. Min Act: -0.0000

Data Index: 68156 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.0314. Min Act: -0.0000

Data Index: 741136 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.0942. Min Act: -0.0000

Data Index: 801443 (C4 (Web Text))

Max Activating Token Index: 919