Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1954 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5800. Min Act: -0.0001

Data Index: 1303968 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1085866 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5657. Min Act: -0.0001

Data Index: 706765 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5792. Min Act: -0.0001

Data Index: 354052 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.6141. Min Act: -0.0001

Data Index: 305584 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1126544 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5512. Min Act: -0.0001

Data Index: 15656 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5686. Min Act: -0.0001

Data Index: 222679 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5498. Min Act: -0.0001

Data Index: 301614 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.4969. Min Act: -0.0001

Data Index: 1048061 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5288. Min Act: -0.0001

Data Index: 1094512 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5681. Min Act: -0.0001

Data Index: 526818 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5383. Min Act: -0.0001

Data Index: 289172 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5410. Min Act: -0.0001

Data Index: 1087981 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5520. Min Act: -0.0001

Data Index: 78832 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1190569 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5266. Min Act: -0.0001

Data Index: 550712 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.4782. Min Act: -0.0001

Data Index: 576207 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5258. Min Act: -0.0001

Data Index: 97704 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5216. Min Act: -0.0001

Data Index: 1015051 (C4 (Web Text))

Max Activating Token Index: 963