Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2957 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.8175. Min Act: -0.0000

Data Index: 1358549 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.5467. Min Act: -0.0000

Data Index: 489271 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.6208. Min Act: -0.0000

Data Index: 689235 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.6122. Min Act: -0.0000

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.5630. Min Act: -0.0000

Data Index: 1221978 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.7058. Min Act: -0.0000

Data Index: 1031346 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.3970. Min Act: -0.0000

Data Index: 779517 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.3200. Min Act: -0.0000

Data Index: 16470 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.3993. Min Act: -0.0000

Data Index: 383686 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.3710. Min Act: -0.0000

Data Index: 755933 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.4620. Min Act: -0.0000

Data Index: 417118 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.4585. Min Act: -0.0000

Data Index: 35711 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.2257. Min Act: -0.0000

Data Index: 103267 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.4337. Min Act: -0.0000

Data Index: 252828 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.3155. Min Act: -0.0000

Data Index: 245629 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.3078. Min Act: -0.0000

Data Index: 1020775 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.2771. Min Act: -0.0000

Data Index: 1283884 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.2637. Min Act: -0.0000

Data Index: 595530 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.2587. Min Act: -0.0000

Data Index: 360968 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 2.8175. Min Range: -2.8175

Max Act: 2.1480. Min Act: -0.0000

Data Index: 876674 (C4 (Web Text))

Max Activating Token Index: 265