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

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

Neuron 2467 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3851. Min Act: -0.0000

Data Index: 127685 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3360. Min Act: -0.0000

Data Index: 107764 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3124. Min Act: 0.0000

Data Index: 723948 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3138. Min Act: -0.0000

Data Index: 254799 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1291819 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2464. Min Act: -0.0000

Data Index: 348496 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2968. Min Act: -0.0000

Data Index: 105892 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2654. Min Act: -0.0000

Data Index: 651684 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3167. Min Act: -0.0000

Data Index: 257042 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2727. Min Act: -0.0000

Data Index: 876477 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2723. Min Act: -0.0000

Data Index: 414671 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2712. Min Act: -0.0000

Data Index: 678172 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2779. Min Act: 0.0000

Data Index: 1242169 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2817. Min Act: 0.0000

Data Index: 67166 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2631. Min Act: -0.0000

Data Index: 239790 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2582. Min Act: 0.0001

Data Index: 825486 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2859. Min Act: 0.0000

Data Index: 1108083 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2668. Min Act: -0.0000

Data Index: 284149 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2771. Min Act: -0.0000

Data Index: 983457 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2678. Min Act: -0.0000

Data Index: 50376 (C4 (Web Text))

Max Activating Token Index: 755