Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4727 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.6438. Min Act: -0.0000

Data Index: 117409 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.6267. Min Act: -0.0000

Data Index: 309626 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.4914. Min Act: -0.0000

Data Index: 485257 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1028855 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.5315. Min Act: -0.0000

Data Index: 758955 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.4534. Min Act: -0.0000

Data Index: 330108 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.5099. Min Act: -0.0000

Data Index: 1635563 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.6911. Min Act: -0.0000

Data Index: 873473 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1338644 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1334782 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.2617. Min Act: -0.0000

Data Index: 44218 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.3859. Min Act: -0.0000

Data Index: 745561 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.3946. Min Act: -0.0000

Data Index: 944863 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.3918. Min Act: -0.0000

Data Index: 1249175 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.3117. Min Act: -0.0000

Data Index: 864488 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.4173. Min Act: -0.0000

Data Index: 101064 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1284257 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.3175. Min Act: -0.0000

Data Index: 681447 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1236853 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 1.7291. Min Range: -1.7291

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1004391 (C4 (Web Text))

Max Activating Token Index: 496