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

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

Neuron 5602 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.2814. Min Act: -0.0000

Data Index: 700763 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.0862. Min Act: -0.0000

Data Index: 678343 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.8927. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.8493. Min Act: -0.0000

Data Index: 744125 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.7879. Min Act: -0.0000

Data Index: 329268 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.7758. Min Act: -0.0000

Data Index: 915833 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.8016. Min Act: -0.0000

Data Index: 54526 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.5890. Min Act: -0.0000

Data Index: 379682 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.7559. Min Act: -0.0000

Data Index: 127947 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.7368. Min Act: -0.0000

Data Index: 630606 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1228626 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.7556. Min Act: -0.0000

Data Index: 101206 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6518. Min Act: -0.0000

Data Index: 263239 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1003653 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6437. Min Act: -0.0000

Data Index: 574161 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1143561 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6809. Min Act: -0.0000

Data Index: 989048 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6922. Min Act: -0.0000

Data Index: 496717 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6412. Min Act: -0.0000

Data Index: 699327 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.6944. Min Act: -0.0000

Data Index: 566419 (C4 (Web Text))

Max Activating Token Index: 910