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

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

Neuron 5956 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: 0.9893. Min Range: -0.9893

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1573101 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1596615 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1614167 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8853. Min Act: -0.0001

Data Index: 1607117 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8959. Min Act: -0.0001

Data Index: 1183203 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8749. Min Act: -0.0001

Data Index: 1582146 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8855. Min Act: -0.0001

Data Index: 1244692 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8656. Min Act: -0.0001

Data Index: 1478460 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8561. Min Act: -0.0001

Data Index: 300476 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8479. Min Act: -0.0001

Data Index: 994167 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1516937 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8402. Min Act: -0.0001

Data Index: 1228715 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8463. Min Act: -0.0001

Data Index: 764964 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8509. Min Act: -0.0001

Data Index: 534402 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1533547 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1416480 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8612. Min Act: -0.0001

Data Index: 49336 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8485. Min Act: -0.0001

Data Index: 1550596 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8484. Min Act: -0.0001

Data Index: 1120431 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8455. Min Act: -0.0001

Data Index: 949101 (C4 (Web Text))

Max Activating Token Index: 989