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

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

Neuron 3587 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.9000. Min Act: -0.0001

Data Index: 1351575 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.9933. Min Act: -0.0001

Data Index: 738925 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.8774. Min Act: -0.0001

Data Index: 1246872 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.7063. Min Act: -0.0001

Data Index: 911264 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.7503. Min Act: -0.0001

Data Index: 1346597 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.6446. Min Act: -0.0001

Data Index: 120358 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.4727. Min Act: -0.0001

Data Index: 211926 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5671. Min Act: -0.0001

Data Index: 343778 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5548. Min Act: -0.0001

Data Index: 74138 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5478. Min Act: -0.0001

Data Index: 370695 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5258. Min Act: -0.0001

Data Index: 523701 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5256. Min Act: -0.0001

Data Index: 626352 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5240. Min Act: -0.0001

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5011. Min Act: -0.0001

Data Index: 1306144 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5829. Min Act: -0.0001

Data Index: 1139337 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.4884. Min Act: -0.0001

Data Index: 216641 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.4094. Min Act: -0.0001

Data Index: 1003129 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.4646. Min Act: -0.0001

Data Index: 57639 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.5456. Min Act: -0.0001

Data Index: 989247 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.9933. Min Range: -1.9933

Max Act: 1.4679. Min Act: -0.0001

Data Index: 349128 (C4 (Web Text))

Max Activating Token Index: 163