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

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

Neuron 1253 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: 0.5554. Min Range: -0.5554

Max Act: 0.5554. Min Act: -0.0001

Data Index: 906055 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3917. Min Act: -0.0000

Data Index: 928632 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1062963 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4092. Min Act: -0.0001

Data Index: 132896 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4221. Min Act: -0.0000

Data Index: 304140 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3781. Min Act: -0.0000

Data Index: 324815 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3755. Min Act: -0.0000

Data Index: 31827 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3646. Min Act: -0.0000

Data Index: 425346 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3601. Min Act: -0.0001

Data Index: 1243782 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1146628 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1207605 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3510. Min Act: -0.0000

Data Index: 499938 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3495. Min Act: -0.0001

Data Index: 116217 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3586. Min Act: -0.0000

Data Index: 911576 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3389. Min Act: -0.0001

Data Index: 1122307 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1177416 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3291. Min Act: -0.0001

Data Index: 1148893 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3390. Min Act: -0.0000

Data Index: 774194 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3358. Min Act: -0.0001

Data Index: 626483 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3238. Min Act: -0.0001

Data Index: 233880 (C4 (Web Text))

Max Activating Token Index: 629