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

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

Neuron 2139 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9468. Min Range: -5.9468

Max Act: 5.9468. Min Act: -0.0001

Data Index: 1018643 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 5.9468. Min Range: -5.9468

Max Act: 5.5359. Min Act: -0.0001

Data Index: 1227704 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 5.9468. Min Range: -5.9468

Max Act: 4.7709. Min Act: -0.0001

Data Index: 14547 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 5.9468. Min Range: -5.9468

Max Act: 4.2694. Min Act: -0.0001

Data Index: 80710 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 5.9468. Min Range: -5.9468

Max Act: 4.1114. Min Act: -0.0001

Data Index: 87405 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 5.9468. Min Range: -5.9468

Max Act: 4.2686. Min Act: -0.0001

Data Index: 821882 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.9306. Min Act: -0.0001

Data Index: 149892 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.8786. Min Act: -0.0001

Data Index: 316466 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 5.9468. Min Range: -5.9468

Max Act: 4.1868. Min Act: -0.0001

Data Index: 80864 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.8870. Min Act: -0.0001

Data Index: 752052 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.2845. Min Act: -0.0001

Data Index: 1231515 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.1075. Min Act: -0.0001

Data Index: 1137488 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.5377. Min Act: -0.0001

Data Index: 1074411 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.1778. Min Act: -0.0001

Data Index: 257806 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.3429. Min Act: -0.0001

Data Index: 1097414 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.1205. Min Act: -0.0001

Data Index: 516840 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.5387. Min Act: -0.0001

Data Index: 515867 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.2824. Min Act: -0.0001

Data Index: 667544 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 5.9468. Min Range: -5.9468

Max Act: 2.9890. Min Act: -0.0001

Data Index: 219121 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 5.9468. Min Range: -5.9468

Max Act: 3.2688. Min Act: -0.0001

Data Index: 221302 (C4 (Web Text))

Max Activating Token Index: 184