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

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

Neuron 3503 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: 1.2081. Min Range: -1.2081

Max Act: 1.2081. Min Act: -0.0000

Data Index: 385210 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.2081. Min Range: -1.2081

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1093117 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.2081. Min Range: -1.2081

Max Act: 1.0105. Min Act: -0.0000

Data Index: 670684 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.2081. Min Range: -1.2081

Max Act: 1.0197. Min Act: -0.0000

Data Index: 40805 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.2081. Min Range: -1.2081

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1146802 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 1.2081. Min Range: -1.2081

Max Act: 1.0023. Min Act: -0.0000

Data Index: 966874 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1200965 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9958. Min Act: -0.0000

Data Index: 707571 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1053912 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9174. Min Act: -0.0000

Data Index: 451278 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9706. Min Act: -0.0000

Data Index: 23641 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9215. Min Act: -0.0000

Data Index: 542316 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1111230 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9326. Min Act: -0.0000

Data Index: 580697 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9778. Min Act: -0.0000

Data Index: 394119 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1084807 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.8252. Min Act: -0.0000

Data Index: 467946 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1176941 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.8780. Min Act: -0.0000

Data Index: 403523 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.2081. Min Range: -1.2081

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1179052 (C4 (Web Text))

Max Activating Token Index: 539