Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3776 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0093. Min Range: -1.0093

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1066336 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7156. Min Act: -0.0000

Data Index: 36572 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7240. Min Act: -0.0000

Data Index: 888764 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6617. Min Act: -0.0000

Data Index: 407518 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1311576 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6250. Min Act: -0.0000

Data Index: 231959 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6321. Min Act: -0.0000

Data Index: 247157 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1268321 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1178414 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5442. Min Act: -0.0000

Data Index: 185780 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1280755 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5804. Min Act: -0.0000

Data Index: 334008 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5481. Min Act: -0.0000

Data Index: 875260 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1259669 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5923. Min Act: -0.0000

Data Index: 279368 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1014019 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1017142 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1127996 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1085631 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.5857. Min Act: -0.0000

Data Index: 802560 (C4 (Web Text))

Max Activating Token Index: 551