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

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

Neuron 1019 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: 0.5009. Min Range: -0.5009

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1472151 (Python Code)

Max Activating Token Index: 134

Text #1

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1479865 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1408604 (Python Code)

Max Activating Token Index: 153

Text #3

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1533121 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1610082 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3870. Min Act: -0.0000

Data Index: 203642 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1374036 (Python Code)

Max Activating Token Index: 186

Text #7

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1583936 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3237. Min Act: -0.0000

Data Index: 989555 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1454442 (Python Code)

Max Activating Token Index: 379

Text #10

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1217080 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3370. Min Act: -0.0000

Data Index: 840126 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1200293 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3330. Min Act: -0.0000

Data Index: 981203 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1430119 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1626423 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3269. Min Act: -0.0000

Data Index: 390683 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3197. Min Act: -0.0000

Data Index: 931276 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1194091 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1555921 (Python Code)

Max Activating Token Index: 371