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

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

Neuron 1815 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: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1586763 (Python Code)

Max Activating Token Index: 406

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1382064 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1639078 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1631107 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1407855 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1583801 (Python Code)

Max Activating Token Index: 273

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1474923 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1530556 (Python Code)

Max Activating Token Index: 216

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1427249 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0497. Min Act: -0.0002

Data Index: 640167 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1092558 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1578169 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1372561 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1145111 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1408490 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1214215 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1466573 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1461338 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1649440 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1036635 (C4 (Web Text))

Max Activating Token Index: 217