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

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

Neuron 1991 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.3355. Min Act: -0.0001

Data Index: 1097715 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2662. Min Act: -0.0001

Data Index: 975091 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1342189 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2701. Min Act: -0.0001

Data Index: 566485 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2596. Min Act: -0.0000

Data Index: 77349 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2664. Min Act: -0.0001

Data Index: 865481 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2290. Min Act: -0.0001

Data Index: 883278 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2259. Min Act: -0.0001

Data Index: 848843 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1301468 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2026. Min Act: -0.0001

Data Index: 644532 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2176. Min Act: -0.0000

Data Index: 636422 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1116755 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2034. Min Act: -0.0001

Data Index: 91311 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1212431 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1828. Min Act: -0.0001

Data Index: 307395 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1962. Min Act: -0.0001

Data Index: 348576 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1299080 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1785. Min Act: -0.0001

Data Index: 607655 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1932. Min Act: -0.0001

Data Index: 744455 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1250712 (C4 (Web Text))

Max Activating Token Index: 754