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

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

Neuron 3015 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2287. Min Act: -0.0003

Data Index: 1161421 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1786. Min Act: -0.0003

Data Index: 206043 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2036. Min Act: -0.0003

Data Index: 1086488 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1916. Min Act: -0.0003

Data Index: 941771 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2136. Min Act: -0.0003

Data Index: 711476 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1758. Min Act: -0.0003

Data Index: 924543 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1817. Min Act: -0.0003

Data Index: 788930 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1681. Min Act: -0.0003

Data Index: 1179528 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1845. Min Act: -0.0003

Data Index: 712595 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1706. Min Act: -0.0003

Data Index: 582099 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1835. Min Act: -0.0003

Data Index: 1101723 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1635. Min Act: -0.0003

Data Index: 633975 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1809. Min Act: -0.0003

Data Index: 1004673 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1499. Min Act: -0.0003

Data Index: 941693 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1549. Min Act: -0.0003

Data Index: 227848 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1612. Min Act: -0.0003

Data Index: 353318 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1699. Min Act: -0.0003

Data Index: 1324220 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1542. Min Act: -0.0003

Data Index: 1132238 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1520. Min Act: -0.0003

Data Index: 1076444 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1522. Min Act: -0.0003

Data Index: 1242243 (C4 (Web Text))

Max Activating Token Index: 840