Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3249 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5474. Min Act: -0.0001

Data Index: 1019583 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5416. Min Act: -0.0001

Data Index: 414840 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5200. Min Act: -0.0001

Data Index: 62680 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5308. Min Act: -0.0001

Data Index: 1087168 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5315. Min Act: -0.0001

Data Index: 1130115 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5105. Min Act: -0.0002

Data Index: 332914 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5300. Min Act: -0.0001

Data Index: 784585 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5131. Min Act: -0.0001

Data Index: 244265 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5134. Min Act: -0.0001

Data Index: 1276035 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5106. Min Act: -0.0001

Data Index: 802125 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5119. Min Act: -0.0001

Data Index: 1324607 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1048910 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5068. Min Act: -0.0001

Data Index: 454426 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4960. Min Act: -0.0002

Data Index: 35553 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4911. Min Act: -0.0001

Data Index: 519779 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4978. Min Act: -0.0001

Data Index: 474314 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4816. Min Act: -0.0001

Data Index: 1047259 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4855. Min Act: -0.0001

Data Index: 265917 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4853. Min Act: -0.0001

Data Index: 287327 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4911. Min Act: -0.0001

Data Index: 950693 (C4 (Web Text))

Max Activating Token Index: 298