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

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

Neuron 3330 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1369159 (Python Code)

Max Activating Token Index: 870

Text #1

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1219126 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3607. Min Act: -0.0000

Data Index: 288810 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1261407 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1488902 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3376. Min Act: -0.0000

Data Index: 689871 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3276. Min Act: -0.0000

Data Index: 67945 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3644. Min Act: -0.0000

Data Index: 684608 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3046. Min Act: -0.0000

Data Index: 10436 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3004. Min Act: -0.0000

Data Index: 522917 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3301. Min Act: -0.0000

Data Index: 567150 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3253. Min Act: -0.0000

Data Index: 973362 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3022. Min Act: -0.0000

Data Index: 600189 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3224. Min Act: -0.0000

Data Index: 309075 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3056. Min Act: -0.0000

Data Index: 103085 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3152. Min Act: -0.0000

Data Index: 722024 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1308198 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2525. Min Act: -0.0000

Data Index: 243282 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2893. Min Act: -0.0000

Data Index: 973005 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2780. Min Act: -0.0000

Data Index: 626001 (C4 (Web Text))

Max Activating Token Index: 658