Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1540 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0003

Data Index: 210785 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1051291 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1049615 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0682. Min Act: -0.0003

Data Index: 438814 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0705. Min Act: -0.0003

Data Index: 57702 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0581. Min Act: -0.0003

Data Index: 524414 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0660. Min Act: -0.0003

Data Index: 809771 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1211703 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0563. Min Act: -0.0003

Data Index: 951810 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1623298 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0584. Min Act: -0.0003

Data Index: 4800 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0562. Min Act: -0.0003

Data Index: 99095 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0534. Min Act: -0.0004

Data Index: 1136687 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1104233 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0610. Min Act: -0.0003

Data Index: 422544 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1001818 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1296573 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0613. Min Act: -0.0003

Data Index: 918744 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0558. Min Act: -0.0003

Data Index: 574193 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0532. Min Act: -0.0003

Data Index: 937385 (C4 (Web Text))

Max Activating Token Index: 479