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

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

Neuron 2572 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4418. Min Act: -0.0003

Data Index: 517962 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2555. Min Act: -0.0003

Data Index: 84298 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4057. Min Act: -0.0003

Data Index: 806811 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.7264. Min Act: -0.0003

Data Index: 2558 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.6702. Min Act: -0.0003

Data Index: 506592 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.1102. Min Act: -0.0003

Data Index: 44809 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3394. Min Act: -0.0003

Data Index: 320908 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5648. Min Act: -0.0003

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4028. Min Act: -0.0003

Data Index: 104189 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4248. Min Act: -0.0003

Data Index: 44673 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3337. Min Act: -0.0003

Data Index: 524700 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4687. Min Act: -0.0003

Data Index: 871555 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3455. Min Act: -0.0003

Data Index: 553182 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5721. Min Act: -0.0003

Data Index: 1185575 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2815. Min Act: -0.0003

Data Index: 964184 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.1009. Min Act: -0.0003

Data Index: 860069 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3503. Min Act: -0.0003

Data Index: 424786 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3287. Min Act: -0.0003

Data Index: 888287 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.1073. Min Act: -0.0003

Data Index: 1315968 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2721. Min Act: -0.0003

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 989