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

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

Neuron 3332 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: 2.4165. Min Range: -2.4165

Max Act: 2.3994. Min Act: -0.0000

Data Index: 781012 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 2.4165. Min Range: -2.4165

Max Act: 2.4165. Min Act: -0.0000

Data Index: 468737 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 2.4165. Min Range: -2.4165

Max Act: 2.1537. Min Act: -0.0000

Data Index: 57644 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 2.4165. Min Range: -2.4165

Max Act: 2.0302. Min Act: -0.0000

Data Index: 1170863 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 2.4165. Min Range: -2.4165

Max Act: 2.0006. Min Act: -0.0000

Data Index: 386726 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.9288. Min Act: -0.0000

Data Index: 248019 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 2.4165. Min Range: -2.4165

Max Act: 2.0232. Min Act: -0.0000

Data Index: 205366 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.7934. Min Act: -0.0000

Data Index: 268920 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.8789. Min Act: -0.0000

Data Index: 986019 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.9665. Min Act: -0.0000

Data Index: 894548 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.8306. Min Act: -0.0000

Data Index: 772385 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 2.4165. Min Range: -2.4165

Max Act: 2.1287. Min Act: -0.0000

Data Index: 694779 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.8748. Min Act: -0.0000

Data Index: 968926 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.8624. Min Act: -0.0000

Data Index: 886191 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.9576. Min Act: -0.0000

Data Index: 272507 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.8535. Min Act: -0.0000

Data Index: 741097 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.8386. Min Act: -0.0000

Data Index: 1073506 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.8053. Min Act: -0.0000

Data Index: 229625 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.6857. Min Act: -0.0000

Data Index: 1169098 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 2.4165. Min Range: -2.4165

Max Act: 1.7792. Min Act: -0.0000

Data Index: 1106271 (C4 (Web Text))

Max Activating Token Index: 425