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

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

Neuron 1286 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: 0.4690. Min Range: -0.4690

Max Act: 0.4690. Min Act: -0.0000

Data Index: 649588 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4379. Min Act: -0.0000

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4562. Min Act: -0.0000

Data Index: 943135 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3852. Min Act: -0.0000

Data Index: 765793 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4444. Min Act: -0.0000

Data Index: 670903 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1468827 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3990. Min Act: -0.0000

Data Index: 824313 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3622. Min Act: -0.0000

Data Index: 942525 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1328668 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1132173 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.2813. Min Act: -0.0000

Data Index: 700862 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3316. Min Act: -0.0000

Data Index: 521540 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.2955. Min Act: -0.0000

Data Index: 974746 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3244. Min Act: -0.0000

Data Index: 269686 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1110264 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3290. Min Act: -0.0000

Data Index: 330591 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1215721 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3012. Min Act: -0.0000

Data Index: 287076 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.4690. Min Range: -0.4690

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1405215 (Python Code)

Max Activating Token Index: 48