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

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

Neuron 2139 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.7056. Min Act: -0.0000

Data Index: 644274 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.4026. Min Act: -0.0000

Data Index: 391175 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.5401. Min Act: -0.0000

Data Index: 779568 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.7141. Min Act: -0.0000

Data Index: 1352039 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.4529. Min Act: -0.0000

Data Index: 136311 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.3409. Min Act: -0.0000

Data Index: 386941 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.3544. Min Act: -0.0000

Data Index: 1023787 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.3285. Min Act: -0.0000

Data Index: 782067 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.0895. Min Act: -0.0000

Data Index: 1031103 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1791. Min Act: -0.0000

Data Index: 1078070 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1276. Min Act: -0.0000

Data Index: 446113 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1790. Min Act: -0.0000

Data Index: 1073062 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.7503. Min Act: -0.0000

Data Index: 745248 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.8896. Min Act: -0.0000

Data Index: 434010 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.6794. Min Act: -0.0000

Data Index: 859961 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.8411. Min Act: -0.0000

Data Index: 457303 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.6337. Min Act: -0.0000

Data Index: 127433 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.3917. Min Act: -0.0000

Data Index: 1064086 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.7480. Min Act: -0.0000

Data Index: 733627 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 5.7141. Min Range: -5.7141

Max Act: 4.5334. Min Act: -0.0000

Data Index: 763879 (C4 (Web Text))

Max Activating Token Index: 239