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

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

Neuron 4175 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: 3.0135. Min Range: -3.0135

Max Act: 2.9088. Min Act: -0.0001

Data Index: 1247178 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.8991. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 3.0135. Min Range: -3.0135

Max Act: 3.0135. Min Act: -0.0001

Data Index: 1301349 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.7379. Min Act: -0.0000

Data Index: 767244 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.7239. Min Act: -0.0001

Data Index: 1108508 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.4239. Min Act: -0.0001

Data Index: 853827 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.4752. Min Act: -0.0001

Data Index: 496615 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.1996. Min Act: -0.0001

Data Index: 871436 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.4059. Min Act: -0.0000

Data Index: 564731 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.4100. Min Act: -0.0001

Data Index: 507510 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.2761. Min Act: -0.0001

Data Index: 177403 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.3913. Min Act: -0.0001

Data Index: 1181456 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.5239. Min Act: -0.0001

Data Index: 758803 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.3797. Min Act: -0.0001

Data Index: 516245 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.3696. Min Act: -0.0001

Data Index: 1178884 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.3336. Min Act: -0.0000

Data Index: 344175 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.3384. Min Act: -0.0001

Data Index: 1030229 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.2126. Min Act: -0.0001

Data Index: 430025 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 3.0135. Min Range: -3.0135

Max Act: 2.2254. Min Act: -0.0001

Data Index: 1251879 (C4 (Web Text))

Max Activating Token Index: 280