Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1435 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1582. Min Range: -2.1582

Max Act: 2.1582. Min Act: -0.0001

Data Index: 1337597 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9011. Min Act: -0.0000

Data Index: 374054 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1351756 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.4982. Min Act: -0.0000

Data Index: 1066981 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.3555. Min Act: -0.0001

Data Index: 978288 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.3822. Min Act: -0.0000

Data Index: 167261 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2584. Min Act: -0.0001

Data Index: 116736 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1220390 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1233092 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1033760 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.1907. Min Act: -0.0001

Data Index: 521707 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2266. Min Act: -0.0000

Data Index: 51054 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1075165 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.0997. Min Act: -0.0001

Data Index: 390415 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2925. Min Act: -0.0001

Data Index: 900076 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.2409. Min Act: -0.0000

Data Index: 66216 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.1281. Min Act: -0.0001

Data Index: 332536 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.1240. Min Act: -0.0000

Data Index: 927590 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.1865. Min Act: -0.0000

Data Index: 901596 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.1482. Min Act: -0.0001

Data Index: 894303 (C4 (Web Text))

Max Activating Token Index: 76