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

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

Neuron 1450 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2142. Min Range: -2.2142

Max Act: 2.2142. Min Act: -0.0000

Data Index: 1193344 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 2.2142. Min Range: -2.2142

Max Act: 2.0041. Min Act: -0.0000

Data Index: 750009 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.6937. Min Act: -0.0000

Data Index: 362573 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1343644 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.5180. Min Act: -0.0000

Data Index: 1338756 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.5152. Min Act: -0.0000

Data Index: 258859 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.5849. Min Act: -0.0000

Data Index: 448435 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.5845. Min Act: -0.0000

Data Index: 186634 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4879. Min Act: -0.0000

Data Index: 660781 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4686. Min Act: -0.0000

Data Index: 585006 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.5525. Min Act: -0.0000

Data Index: 741530 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.5322. Min Act: -0.0000

Data Index: 752077 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.5009. Min Act: -0.0000

Data Index: 231570 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4979. Min Act: -0.0000

Data Index: 1091073 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1293957 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.3648. Min Act: -0.0000

Data Index: 642484 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4530. Min Act: -0.0000

Data Index: 507385 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4416. Min Act: -0.0000

Data Index: 300851 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4380. Min Act: -0.0000

Data Index: 1086656 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 2.2142. Min Range: -2.2142

Max Act: 1.4930. Min Act: -0.0000

Data Index: 304335 (C4 (Web Text))

Max Activating Token Index: 425