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

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

Neuron 158 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.3784. Min Act: -0.0000

Data Index: 683757 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.3283. Min Act: -0.0000

Data Index: 1297548 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.3336. Min Act: -0.0000

Data Index: 660440 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1161515 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1309354 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1703. Min Act: -0.0000

Data Index: 869884 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1732. Min Act: -0.0000

Data Index: 675371 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1304. Min Act: -0.0000

Data Index: 40447 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1355603 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1655. Min Act: -0.0000

Data Index: 744836 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1339. Min Act: -0.0000

Data Index: 114494 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.0936. Min Act: -0.0000

Data Index: 804272 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1146. Min Act: -0.0000

Data Index: 295808 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1375680 (Python Code)

Max Activating Token Index: 381

Text #14

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1242. Min Act: -0.0000

Data Index: 168264 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.0863. Min Act: -0.0000

Data Index: 164964 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.0962. Min Act: -0.0000

Data Index: 523251 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.0806. Min Act: -0.0000

Data Index: 901160 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1284553 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.3784. Min Range: -1.3784

Max Act: 1.0462. Min Act: -0.0000

Data Index: 560609 (C4 (Web Text))

Max Activating Token Index: 667