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

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

Neuron 2324 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0556. Min Act: -0.0002

Data Index: 339833 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0555. Min Act: -0.0002

Data Index: 959427 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1018191 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0542. Min Act: -0.0002

Data Index: 187565 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0549. Min Act: -0.0002

Data Index: 247560 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1278592 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0540. Min Act: -0.0002

Data Index: 691454 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0527. Min Act: -0.0002

Data Index: 520960 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1523933 (Python Code)

Max Activating Token Index: 294

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1145180 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0531. Min Act: -0.0002

Data Index: 613591 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1139474 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1162116 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0526. Min Act: -0.0002

Data Index: 15465 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1445669 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0531. Min Act: -0.0002

Data Index: 871506 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1006287 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0521. Min Act: -0.0002

Data Index: 816653 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1505448 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1324106 (C4 (Web Text))

Max Activating Token Index: 610