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

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

Neuron 4618 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8283. Min Range: -4.8283

Max Act: 4.8283. Min Act: -0.0000

Data Index: 841899 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 4.8283. Min Range: -4.8283

Max Act: 4.3750. Min Act: -0.0000

Data Index: 820051 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 4.8283. Min Range: -4.8283

Max Act: 4.2920. Min Act: -0.0000

Data Index: 934845 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 4.8283. Min Range: -4.8283

Max Act: 4.0709. Min Act: -0.0000

Data Index: 1155545 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 4.8283. Min Range: -4.8283

Max Act: 4.0351. Min Act: -0.0000

Data Index: 577482 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 4.8283. Min Range: -4.8283

Max Act: 4.1250. Min Act: -0.0000

Data Index: 861437 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.7841. Min Act: -0.0000

Data Index: 1309820 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.3515. Min Act: -0.0000

Data Index: 354636 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.9940. Min Act: -0.0000

Data Index: 528166 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.8032. Min Act: -0.0000

Data Index: 537803 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.6130. Min Act: -0.0000

Data Index: 214814 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.9311. Min Act: -0.0000

Data Index: 1149768 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.7310. Min Act: -0.0000

Data Index: 1225405 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.5388. Min Act: -0.0000

Data Index: 458567 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.8208. Min Act: -0.0000

Data Index: 156063 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.3923. Min Act: -0.0000

Data Index: 731006 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.7438. Min Act: -0.0000

Data Index: 498634 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.3833. Min Act: -0.0000

Data Index: 425690 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.7141. Min Act: -0.0000

Data Index: 935952 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 4.8283. Min Range: -4.8283

Max Act: 3.4829. Min Act: -0.0000

Data Index: 634929 (C4 (Web Text))

Max Activating Token Index: 754