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

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

Neuron 1647 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1361. Min Range: -2.1361

Max Act: 2.1361. Min Act: -0.0000

Data Index: 1311233 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.8256. Min Act: -0.0000

Data Index: 20793 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.5731. Min Act: -0.0000

Data Index: 526532 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.5034. Min Act: -0.0000

Data Index: 846816 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1123667 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.4501. Min Act: -0.0000

Data Index: 992331 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1079031 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1326164 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1151585 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1277487 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.2876. Min Act: -0.0000

Data Index: 203501 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.3711. Min Act: -0.0000

Data Index: 169072 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.4387. Min Act: -0.0000

Data Index: 934493 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1157939 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.2584. Min Act: -0.0000

Data Index: 766670 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.3351. Min Act: -0.0000

Data Index: 22284 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.3309. Min Act: -0.0000

Data Index: 512006 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.4129. Min Act: -0.0000

Data Index: 800021 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.2213. Min Act: -0.0000

Data Index: 452807 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 2.1361. Min Range: -2.1361

Max Act: 1.2298. Min Act: -0.0000

Data Index: 1322205 (C4 (Web Text))

Max Activating Token Index: 124