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

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

Neuron 256 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: 1.8974. Min Range: -1.8974

Max Act: 1.8974. Min Act: -0.0000

Data Index: 979238 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.7081. Min Act: -0.0000

Data Index: 317496 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.7965. Min Act: -0.0000

Data Index: 205835 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5559. Min Act: -0.0000

Data Index: 198453 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5411. Min Act: -0.0000

Data Index: 848875 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.5817. Min Act: -0.0000

Data Index: 95411 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1184222 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.3522. Min Act: -0.0000

Data Index: 974296 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.3747. Min Act: -0.0000

Data Index: 667901 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.2657. Min Act: -0.0000

Data Index: 360690 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1212955 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.2804. Min Act: -0.0000

Data Index: 238103 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.2302. Min Act: -0.0000

Data Index: 329004 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.2514. Min Act: -0.0000

Data Index: 320942 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.2359. Min Act: -0.0000

Data Index: 24803 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.1886. Min Act: -0.0000

Data Index: 167894 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.1672. Min Act: -0.0000

Data Index: 327493 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.1967. Min Act: -0.0000

Data Index: 406245 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.1499. Min Act: -0.0000

Data Index: 644133 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.8974. Min Range: -1.8974

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1180303 (C4 (Web Text))

Max Activating Token Index: 928