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

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

Neuron 1360 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: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0002

Data Index: 676713 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0600. Min Act: -0.0002

Data Index: 846552 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0583. Min Act: -0.0002

Data Index: 792891 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0580. Min Act: -0.0002

Data Index: 561498 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1253417 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1232907 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0574. Min Act: -0.0002

Data Index: 609329 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1337358 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0550. Min Act: -0.0002

Data Index: 717988 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0556. Min Act: -0.0002

Data Index: 109529 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0551. Min Act: -0.0002

Data Index: 38861 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1062412 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0548. Min Act: -0.0002

Data Index: 693091 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1391817 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0543. Min Act: -0.0002

Data Index: 139004 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1328193 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0533. Min Act: -0.0002

Data Index: 779029 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1183199 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0559. Min Act: -0.0002

Data Index: 208552 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0543. Min Act: -0.0002

Data Index: 457264 (C4 (Web Text))

Max Activating Token Index: 644