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

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

Neuron 152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0740. Min Act: -0.0001

Data Index: 285936 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0390. Min Act: -0.0001

Data Index: 270307 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 3.0740. Min Range: -3.0740

Max Act: 3.0176. Min Act: -0.0001

Data Index: 1178499 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.4473. Min Act: -0.0000

Data Index: 897735 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.3474. Min Act: -0.0001

Data Index: 459156 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.3142. Min Act: -0.0001

Data Index: 1337089 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.2821. Min Act: -0.0000

Data Index: 480187 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.2458. Min Act: -0.0001

Data Index: 1068697 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.0300. Min Act: -0.0001

Data Index: 656255 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.1042. Min Act: -0.0001

Data Index: 1316188 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.1542. Min Act: -0.0001

Data Index: 348971 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.1400. Min Act: -0.0000

Data Index: 859003 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.2684. Min Act: -0.0001

Data Index: 918707 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.1971. Min Act: -0.0001

Data Index: 473704 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.1679. Min Act: -0.0001

Data Index: 391297 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.0795. Min Act: -0.0001

Data Index: 1131292 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.0642. Min Act: -0.0001

Data Index: 722717 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.0406. Min Act: -0.0001

Data Index: 1188954 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.0465. Min Act: -0.0001

Data Index: 182462 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 3.0740. Min Range: -3.0740

Max Act: 2.0345. Min Act: -0.0000

Data Index: 818236 (C4 (Web Text))

Max Activating Token Index: 396