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

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

Neuron 30 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2313. Min Range: -5.2313

Max Act: 5.2313. Min Act: -0.0000

Data Index: 400988 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 5.2313. Min Range: -5.2313

Max Act: 4.3618. Min Act: -0.0000

Data Index: 1051155 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 5.2313. Min Range: -5.2313

Max Act: 4.4978. Min Act: -0.0000

Data Index: 1123494 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 5.2313. Min Range: -5.2313

Max Act: 4.3136. Min Act: -0.0000

Data Index: 600336 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 5.2313. Min Range: -5.2313

Max Act: 4.1140. Min Act: -0.0000

Data Index: 427034 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.9888. Min Act: -0.0000

Data Index: 60629 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.8530. Min Act: -0.0001

Data Index: 1294201 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 5.2313. Min Range: -5.2313

Max Act: 4.0103. Min Act: -0.0000

Data Index: 14393 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.4613. Min Act: -0.0000

Data Index: 1165775 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.6441. Min Act: -0.0001

Data Index: 377999 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.3197. Min Act: -0.0000

Data Index: 732898 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.3841. Min Act: -0.0000

Data Index: 348003 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.6244. Min Act: -0.0000

Data Index: 271977 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.7702. Min Act: -0.0000

Data Index: 273020 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.7683. Min Act: -0.0000

Data Index: 375141 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.4015. Min Act: -0.0000

Data Index: 238888 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.5303. Min Act: -0.0000

Data Index: 1234893 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.2842. Min Act: -0.0000

Data Index: 1003743 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.6096. Min Act: -0.0000

Data Index: 207384 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 5.2313. Min Range: -5.2313

Max Act: 3.4002. Min Act: -0.0000

Data Index: 1331435 (C4 (Web Text))

Max Activating Token Index: 919