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

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

Neuron 2454 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: 3.4654. Min Range: -3.4654

Max Act: 3.4654. Min Act: -0.0000

Data Index: 338868 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.0386. Min Act: -0.0000

Data Index: 800009 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.9789. Min Act: -0.0000

Data Index: 1091071 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.9659. Min Act: -0.0000

Data Index: 1240920 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.8302. Min Act: -0.0000

Data Index: 444620 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.8240. Min Act: -0.0000

Data Index: 456745 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.8573. Min Act: -0.0000

Data Index: 494835 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.7186. Min Act: -0.0000

Data Index: 1184948 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.6757. Min Act: -0.0000

Data Index: 983857 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.6050. Min Act: -0.0000

Data Index: 143142 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.4963. Min Act: -0.0000

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.7512. Min Act: -0.0000

Data Index: 320630 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.5937. Min Act: -0.0000

Data Index: 91406 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.6984. Min Act: -0.0000

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.5435. Min Act: -0.0000

Data Index: 96040 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1279523 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.2591. Min Act: -0.0000

Data Index: 225389 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.4971. Min Act: -0.0000

Data Index: 171115 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.3582. Min Act: -0.0000

Data Index: 29429 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 3.4654. Min Range: -3.4654

Max Act: 2.4126. Min Act: -0.0000

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 809