Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 543 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.9527. Min Act: -0.0001

Data Index: 561194 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8532. Min Act: -0.0001

Data Index: 1018634 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8709. Min Act: -0.0001

Data Index: 45695 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8670. Min Act: -0.0001

Data Index: 813720 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8906. Min Act: -0.0001

Data Index: 699423 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8813. Min Act: -0.0001

Data Index: 908913 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.9222. Min Act: -0.0001

Data Index: 137718 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8723. Min Act: -0.0001

Data Index: 382015 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8750. Min Act: -0.0001

Data Index: 781672 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8825. Min Act: -0.0000

Data Index: 33013 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8534. Min Act: -0.0001

Data Index: 921745 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8528. Min Act: -0.0001

Data Index: 693289 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8188. Min Act: -0.0001

Data Index: 341725 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8197. Min Act: -0.0001

Data Index: 1337431 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7889. Min Act: -0.0001

Data Index: 1317352 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8238. Min Act: -0.0001

Data Index: 336134 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7974. Min Act: -0.0001

Data Index: 955570 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8099. Min Act: -0.0001

Data Index: 219441 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7493. Min Act: -0.0001

Data Index: 673653 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7702. Min Act: -0.0001

Data Index: 354598 (C4 (Web Text))

Max Activating Token Index: 712