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

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

Neuron 2640 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1380372 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5934. Min Act: -0.0000

Data Index: 86779 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1569417 (Python Code)

Max Activating Token Index: 597

Text #3

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5112. Min Act: -0.0000

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5139. Min Act: -0.0000

Data Index: 58559 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1634207 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1483391 (Python Code)

Max Activating Token Index: 441

Text #7

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1503232 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4436. Min Act: -0.0000

Data Index: 934341 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1581173 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4504. Min Act: -0.0000

Data Index: 216985 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1465762 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4772. Min Act: -0.0000

Data Index: 93161 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4923. Min Act: -0.0000

Data Index: 377853 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1315784 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4440. Min Act: -0.0000

Data Index: 372114 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4658. Min Act: -0.0000

Data Index: 475634 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1236265 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1519719 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1267755 (C4 (Web Text))

Max Activating Token Index: 961