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

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

Neuron 5836 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8830. Min Act: -0.0000

Data Index: 154812 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7959. Min Act: -0.0000

Data Index: 467016 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6322. Min Act: -0.0000

Data Index: 511393 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7198. Min Act: -0.0000

Data Index: 148968 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6287. Min Act: -0.0000

Data Index: 994115 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.5328. Min Act: -0.0000

Data Index: 1157711 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6714. Min Act: -0.0000

Data Index: 1126561 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4950. Min Act: -0.0001

Data Index: 372011 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1344765 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1247442 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.3559. Min Act: -0.0000

Data Index: 998042 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.5100. Min Act: -0.0000

Data Index: 477726 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4020. Min Act: -0.0000

Data Index: 617649 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4744. Min Act: -0.0000

Data Index: 1261147 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4233. Min Act: -0.0000

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4490. Min Act: -0.0001

Data Index: 592549 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4268. Min Act: -0.0000

Data Index: 1233220 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1306400 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4324. Min Act: -0.0001

Data Index: 415427 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.2622. Min Act: -0.0000

Data Index: 500216 (C4 (Web Text))

Max Activating Token Index: 374