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

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

Neuron 3285 in Layer 0

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: 0.3980. Min Range: -0.3980

Max Act: 0.3980. Min Act: -0.0001

Data Index: 444687 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3828. Min Act: -0.0001

Data Index: 315924 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3798. Min Act: -0.0001

Data Index: 295823 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3905. Min Act: -0.0001

Data Index: 1080467 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3801. Min Act: -0.0001

Data Index: 645992 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3803. Min Act: -0.0001

Data Index: 327652 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3616. Min Act: -0.0001

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3582. Min Act: -0.0001

Data Index: 710534 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3620. Min Act: -0.0001

Data Index: 480515 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3573. Min Act: -0.0001

Data Index: 404788 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3548. Min Act: -0.0001

Data Index: 573909 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3537. Min Act: -0.0001

Data Index: 740729 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3583. Min Act: -0.0001

Data Index: 645901 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3516. Min Act: -0.0001

Data Index: 321440 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3477. Min Act: -0.0001

Data Index: 712905 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3562. Min Act: -0.0001

Data Index: 501003 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3577. Min Act: -0.0002

Data Index: 122186 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3561. Min Act: -0.0001

Data Index: 1612889 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3532. Min Act: -0.0001

Data Index: 268811 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3466. Min Act: -0.0001

Data Index: 257328 (C4 (Web Text))

Max Activating Token Index: 278