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

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

Neuron 5075 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.7399. Min Act: -0.0001

Data Index: 1148754 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.6023. Min Act: -0.0001

Data Index: 567053 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.5884. Min Act: -0.0001

Data Index: 192984 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4159. Min Act: -0.0001

Data Index: 1338188 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.4058. Min Act: -0.0001

Data Index: 944312 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.3768. Min Act: -0.0001

Data Index: 390656 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.3729. Min Act: -0.0001

Data Index: 911526 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.3458. Min Act: -0.0001

Data Index: 819613 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1201831 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2891. Min Act: -0.0001

Data Index: 312791 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2571. Min Act: -0.0001

Data Index: 1202115 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2992. Min Act: -0.0001

Data Index: 94440 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.3068. Min Act: -0.0001

Data Index: 78898 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2969. Min Act: -0.0001

Data Index: 712665 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2889. Min Act: -0.0001

Data Index: 1058295 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2577. Min Act: -0.0001

Data Index: 754507 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2900. Min Act: -0.0001

Data Index: 602092 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2908. Min Act: -0.0001

Data Index: 451971 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2814. Min Act: -0.0001

Data Index: 340363 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.7399. Min Range: -0.7399

Max Act: 0.2885. Min Act: -0.0001

Data Index: 523172 (C4 (Web Text))

Max Activating Token Index: 144