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

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

Neuron 1169 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1234085 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7634. Min Act: -0.0001

Data Index: 1349416 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6371. Min Act: -0.0001

Data Index: 1094096 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.7000. Min Act: -0.0001

Data Index: 779922 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6696. Min Act: -0.0001

Data Index: 691796 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1236913 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.6374. Min Act: -0.0001

Data Index: 873491 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5795. Min Act: -0.0001

Data Index: 539770 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5988. Min Act: -0.0001

Data Index: 1034693 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5252. Min Act: -0.0001

Data Index: 471817 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5799. Min Act: -0.0001

Data Index: 669983 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5736. Min Act: -0.0001

Data Index: 178156 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5901. Min Act: -0.0001

Data Index: 640639 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5328. Min Act: -0.0001

Data Index: 1334111 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5498. Min Act: -0.0001

Data Index: 1296352 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5197. Min Act: -0.0001

Data Index: 1253304 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5387. Min Act: -0.0001

Data Index: 836926 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5169. Min Act: -0.0001

Data Index: 424271 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5346. Min Act: -0.0001

Data Index: 661752 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.8104. Min Range: -0.8104

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1164712 (C4 (Web Text))

Max Activating Token Index: 241