Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2163 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.8500. Min Act: -0.0001

Data Index: 1004018 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.9468. Min Act: -0.0001

Data Index: 1221725 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.7101. Min Act: -0.0001

Data Index: 1086381 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.8832. Min Act: -0.0001

Data Index: 844534 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.6527. Min Act: -0.0001

Data Index: 414204 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.6964. Min Act: -0.0001

Data Index: 908569 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.6800. Min Act: -0.0001

Data Index: 198118 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.5672. Min Act: -0.0001

Data Index: 926345 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.5667. Min Act: -0.0001

Data Index: 696810 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4209. Min Act: -0.0001

Data Index: 466908 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.6806. Min Act: -0.0001

Data Index: 680480 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4898. Min Act: -0.0001

Data Index: 730957 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4407. Min Act: -0.0001

Data Index: 1353765 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.5590. Min Act: -0.0001

Data Index: 1306836 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4969. Min Act: -0.0001

Data Index: 831451 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4040. Min Act: -0.0001

Data Index: 470302 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4692. Min Act: -0.0001

Data Index: 1072041 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4252. Min Act: -0.0001

Data Index: 472173 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.4175. Min Act: -0.0001

Data Index: 738052 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2840. Min Act: -0.0001

Data Index: 1359597 (C4 (Web Text))

Max Activating Token Index: 279