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

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

Neuron 3272 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1067637 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5517. Min Act: -0.0000

Data Index: 635758 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5199. Min Act: -0.0000

Data Index: 154153 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1054094 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3015. Min Act: -0.0000

Data Index: 547868 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1675. Min Act: -0.0000

Data Index: 277175 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1298047 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1006365 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0172. Min Act: -0.0000

Data Index: 13686 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1328164 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9502. Min Act: -0.0000

Data Index: 758945 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0326. Min Act: -0.0000

Data Index: 967518 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9175. Min Act: -0.0000

Data Index: 468341 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1098058 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1163299 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1076117 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1157179 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1035881 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.8284. Min Act: -0.0000

Data Index: 705794 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.8336. Min Act: -0.0000

Data Index: 858661 (C4 (Web Text))

Max Activating Token Index: 1001