Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4458 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.5137. Min Act: -0.0000

Data Index: 638248 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4500. Min Act: -0.0000

Data Index: 589355 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1000717 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3892. Min Act: -0.0000

Data Index: 736629 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1333221 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3588. Min Act: -0.0000

Data Index: 974415 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3734. Min Act: -0.0000

Data Index: 76696 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3767. Min Act: -0.0000

Data Index: 394560 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3505. Min Act: -0.0000

Data Index: 664105 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3470. Min Act: -0.0000

Data Index: 674143 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3604. Min Act: -0.0000

Data Index: 787787 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3308. Min Act: -0.0000

Data Index: 55971 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3220. Min Act: -0.0000

Data Index: 675600 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3507. Min Act: -0.0000

Data Index: 977839 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3380. Min Act: -0.0000

Data Index: 896101 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3207. Min Act: -0.0000

Data Index: 5758 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3195. Min Act: -0.0000

Data Index: 23702 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3297. Min Act: -0.0000

Data Index: 871226 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1051038 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3167. Min Act: -0.0000

Data Index: 484513 (C4 (Web Text))

Max Activating Token Index: 1021