Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3323 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.9313. Min Act: -0.0001

Data Index: 1383123 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.9321. Min Act: -0.0001

Data Index: 1432116 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.9566. Min Act: -0.0001

Data Index: 1622409 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.8847. Min Act: -0.0001

Data Index: 1535961 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.8730. Min Act: -0.0001

Data Index: 1634620 (Python Code)

Max Activating Token Index: 1004

Text #5

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.9202. Min Act: -0.0001

Data Index: 1430321 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.8670. Min Act: -0.0001

Data Index: 1543797 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1377025 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7051. Min Act: -0.0001

Data Index: 1537038 (Python Code)

Max Activating Token Index: 479

Text #9

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7655. Min Act: -0.0001

Data Index: 1426211 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.8689. Min Act: -0.0001

Data Index: 1439268 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7183. Min Act: -0.0001

Data Index: 1451353 (Python Code)

Max Activating Token Index: 395

Text #12

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7797. Min Act: -0.0001

Data Index: 1602905 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7367. Min Act: -0.0001

Data Index: 1507675 (Python Code)

Max Activating Token Index: 1006

Text #14

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1571835 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7208. Min Act: -0.0001

Data Index: 1533148 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7659. Min Act: -0.0001

Data Index: 1441688 (Python Code)

Max Activating Token Index: 290

Text #17

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.6764. Min Act: -0.0001

Data Index: 432547 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1399768 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 0.9566. Min Range: -0.9566

Max Act: 0.6797. Min Act: -0.0001

Data Index: 1367214 (Python Code)

Max Activating Token Index: 283