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

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

Neuron 5828 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1289182 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2919. Min Act: -0.0000

Data Index: 765868 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2911. Min Act: -0.0000

Data Index: 16400 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2948. Min Act: -0.0000

Data Index: 14565 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3031. Min Act: -0.0000

Data Index: 580638 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2874. Min Act: 0.0000

Data Index: 668858 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2833. Min Act: -0.0000

Data Index: 604615 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1253482 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1160527 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1004042 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2873. Min Act: -0.0000

Data Index: 430835 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1085681 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1330089 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2532. Min Act: -0.0000

Data Index: 226472 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1287077 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2443. Min Act: 0.0000

Data Index: 650429 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2658. Min Act: -0.0000

Data Index: 992729 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2424. Min Act: -0.0000

Data Index: 2798 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2521. Min Act: -0.0000

Data Index: 899124 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2552. Min Act: -0.0000

Data Index: 239292 (C4 (Web Text))

Max Activating Token Index: 328