Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 914 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2241. Min Act: -0.0001

Data Index: 653395 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1971. Min Act: -0.0001

Data Index: 267425 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1946. Min Act: -0.0001

Data Index: 403318 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1205799 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1822. Min Act: -0.0001

Data Index: 304088 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1819. Min Act: -0.0001

Data Index: 400732 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1797. Min Act: -0.0001

Data Index: 433297 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1790. Min Act: -0.0001

Data Index: 717616 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1696. Min Act: -0.0001

Data Index: 898157 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1723. Min Act: -0.0001

Data Index: 1105995 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1697. Min Act: -0.0001

Data Index: 622425 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1651. Min Act: -0.0001

Data Index: 729863 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1664. Min Act: -0.0001

Data Index: 46874 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1586. Min Act: -0.0001

Data Index: 107649 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1605. Min Act: -0.0001

Data Index: 419417 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1589. Min Act: -0.0001

Data Index: 534344 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1171319 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1522. Min Act: -0.0001

Data Index: 627695 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1619. Min Act: -0.0001

Data Index: 914597 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1191612 (C4 (Web Text))

Max Activating Token Index: 902