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

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

Neuron 2720 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.7767. Min Act: -0.0000

Data Index: 1014020 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.1275. Min Act: -0.0000

Data Index: 563817 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.4030. Min Act: -0.0000

Data Index: 920097 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.3280. Min Act: -0.0000

Data Index: 474628 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 5.7767. Min Range: -5.7767

Max Act: 4.9431. Min Act: -0.0000

Data Index: 345907 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.1432. Min Act: -0.0000

Data Index: 1165885 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.0154. Min Act: -0.0000

Data Index: 780916 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.0091. Min Act: -0.0000

Data Index: 632768 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.1216. Min Act: -0.0000

Data Index: 824109 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 5.7767. Min Range: -5.7767

Max Act: 4.7810. Min Act: -0.0000

Data Index: 1175984 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.1227. Min Act: -0.0000

Data Index: 238962 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.0449. Min Act: -0.0000

Data Index: 644123 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 5.7767. Min Range: -5.7767

Max Act: 4.9799. Min Act: -0.0001

Data Index: 1323144 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 5.7767. Min Range: -5.7767

Max Act: 4.8094. Min Act: -0.0000

Data Index: 1169985 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.2788. Min Act: -0.0000

Data Index: 289830 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.1003. Min Act: -0.0000

Data Index: 691002 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 5.7767. Min Range: -5.7767

Max Act: 4.5505. Min Act: -0.0000

Data Index: 1071057 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 5.7767. Min Range: -5.7767

Max Act: 5.0478. Min Act: -0.0000

Data Index: 580510 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 5.7767. Min Range: -5.7767

Max Act: 4.7640. Min Act: -0.0000

Data Index: 347266 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 5.7767. Min Range: -5.7767

Max Act: 4.7384. Min Act: -0.0000

Data Index: 1140075 (C4 (Web Text))

Max Activating Token Index: 441