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

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

Neuron 1309 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0002

Data Index: 111014 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1166767 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0694. Min Act: -0.0002

Data Index: 388717 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0708. Min Act: -0.0002

Data Index: 206858 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0701. Min Act: -0.0002

Data Index: 212192 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0672. Min Act: -0.0002

Data Index: 317936 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0690. Min Act: -0.0002

Data Index: 996775 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1062970 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0645. Min Act: -0.0001

Data Index: 19645 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0670. Min Act: -0.0002

Data Index: 417783 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1128779 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0639. Min Act: -0.0002

Data Index: 176252 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0607. Min Act: -0.0002

Data Index: 472150 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0607. Min Act: -0.0002

Data Index: 502029 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0596. Min Act: -0.0002

Data Index: 48837 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0593. Min Act: -0.0002

Data Index: 293424 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0576. Min Act: -0.0002

Data Index: 609681 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0606. Min Act: -0.0002

Data Index: 249849 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0555. Min Act: -0.0002

Data Index: 920800 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0578. Min Act: -0.0002

Data Index: 317823 (C4 (Web Text))

Max Activating Token Index: 463