Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 361 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0457. Min Act: -0.0000

Data Index: 339159 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.2268. Min Act: -0.0000

Data Index: 1302496 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.1932. Min Act: -0.0000

Data Index: 242822 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.2940. Min Act: -0.0000

Data Index: 96566 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.2800. Min Act: -0.0000

Data Index: 21949 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.2595. Min Act: -0.0000

Data Index: 1122619 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.1463. Min Act: -0.0000

Data Index: 286889 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0368. Min Act: -0.0000

Data Index: 573477 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.2319. Min Act: -0.0000

Data Index: 863142 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0716. Min Act: -0.0000

Data Index: 791202 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0760. Min Act: -0.0000

Data Index: 1232826 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1180558 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0643. Min Act: -0.0000

Data Index: 154761 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0408. Min Act: -0.0000

Data Index: 979690 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.1523. Min Act: -0.0000

Data Index: 552026 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0237. Min Act: -0.0000

Data Index: 1062813 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 2.2940. Min Range: -2.2940

Max Act: 1.9215. Min Act: -0.0000

Data Index: 71184 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0117. Min Act: -0.0000

Data Index: 248130 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0180. Min Act: -0.0000

Data Index: 637026 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 2.2940. Min Range: -2.2940

Max Act: 2.0995. Min Act: -0.0000

Data Index: 1312907 (C4 (Web Text))

Max Activating Token Index: 240