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

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

Neuron 840 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: 0.2497. Min Range: -0.2497

Max Act: 0.2497. Min Act: -0.0001

Data Index: 386112 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2085. Min Act: -0.0001

Data Index: 18128 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2119. Min Act: -0.0001

Data Index: 68068 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1250130 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2005. Min Act: -0.0001

Data Index: 888936 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2091. Min Act: -0.0001

Data Index: 899589 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2122. Min Act: -0.0001

Data Index: 403841 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2189. Min Act: -0.0001

Data Index: 586105 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2030. Min Act: -0.0001

Data Index: 11698 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1792. Min Act: -0.0001

Data Index: 870245 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2043. Min Act: -0.0001

Data Index: 140545 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1885. Min Act: -0.0001

Data Index: 351074 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1893. Min Act: -0.0001

Data Index: 590544 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1786. Min Act: -0.0001

Data Index: 927873 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1829. Min Act: -0.0001

Data Index: 277397 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1923. Min Act: -0.0001

Data Index: 595207 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1856. Min Act: -0.0001

Data Index: 939542 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1776. Min Act: -0.0001

Data Index: 240442 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1834. Min Act: -0.0001

Data Index: 514995 (C4 (Web Text))

Max Activating Token Index: 425