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

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

Neuron 2251 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2352. Min Act: -0.0001

Data Index: 1217888 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0001

Data Index: 222008 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2740. Min Act: -0.0001

Data Index: 577924 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2454. Min Act: -0.0001

Data Index: 650898 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2336. Min Act: -0.0001

Data Index: 932797 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2326. Min Act: -0.0001

Data Index: 1059584 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2167. Min Act: -0.0001

Data Index: 79928 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1039572 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2119. Min Act: -0.0001

Data Index: 240272 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1253228 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1172144 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2012. Min Act: -0.0001

Data Index: 124763 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1002750 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2148. Min Act: -0.0001

Data Index: 196467 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1972. Min Act: -0.0001

Data Index: 194943 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2015. Min Act: -0.0001

Data Index: 885423 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1923. Min Act: -0.0001

Data Index: 779527 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1765. Min Act: -0.0001

Data Index: 588797 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1268949 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1163110 (C4 (Web Text))

Max Activating Token Index: 727