Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 456 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0005

Data Index: 203729 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1066318 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0005

Data Index: 495964 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0110. Min Act: -0.0005

Data Index: 225095 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0113. Min Act: -0.0005

Data Index: 767530 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0005

Data Index: 851283 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0101. Min Act: -0.0005

Data Index: 746215 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0005

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0005

Data Index: 433351 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0111. Min Act: -0.0005

Data Index: 375009 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0093. Min Act: -0.0005

Data Index: 939043 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0106. Min Act: -0.0005

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0106. Min Act: -0.0005

Data Index: 386267 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0098. Min Act: -0.0005

Data Index: 120142 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1599117 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0107. Min Act: -0.0005

Data Index: 787849 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0101. Min Act: -0.0005

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0104. Min Act: -0.0005

Data Index: 632291 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0107. Min Act: -0.0005

Data Index: 163729 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0104. Min Act: -0.0005

Data Index: 337301 (C4 (Web Text))

Max Activating Token Index: 260