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

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

Neuron 3599 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: 0.5584. Min Range: -0.5584

Max Act: 0.5584. Min Act: -0.0000

Data Index: 306046 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.5200. Min Act: -0.0001

Data Index: 912797 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.5178. Min Act: -0.0000

Data Index: 323024 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1032327 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4965. Min Act: -0.0000

Data Index: 980098 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4749. Min Act: -0.0000

Data Index: 637415 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4786. Min Act: -0.0000

Data Index: 767603 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1063495 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4539. Min Act: -0.0001

Data Index: 868454 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4866. Min Act: -0.0001

Data Index: 340294 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4658. Min Act: -0.0001

Data Index: 1263576 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1071401 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4495. Min Act: -0.0000

Data Index: 637040 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4479. Min Act: -0.0001

Data Index: 1125417 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1125102 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1329259 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4413. Min Act: -0.0001

Data Index: 502055 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4422. Min Act: -0.0000

Data Index: 847844 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4091. Min Act: -0.0000

Data Index: 257792 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.5584. Min Range: -0.5584

Max Act: 0.4213. Min Act: -0.0001

Data Index: 1177246 (C4 (Web Text))

Max Activating Token Index: 354