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

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

Neuron 1418 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3645. Min Act: -0.0000

Data Index: 238654 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3095. Min Act: -0.0000

Data Index: 146579 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.4432. Min Act: -0.0000

Data Index: 835451 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1300787 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.4261. Min Act: -0.0000

Data Index: 689595 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3145. Min Act: -0.0000

Data Index: 10823 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3799. Min Act: -0.0000

Data Index: 157002 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3305. Min Act: -0.0000

Data Index: 360262 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3129. Min Act: -0.0000

Data Index: 626050 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3229. Min Act: -0.0000

Data Index: 1173796 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1043114 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.2968. Min Act: -0.0000

Data Index: 499819 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.2279. Min Act: -0.0000

Data Index: 671459 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1098806 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.2493. Min Act: -0.0000

Data Index: 470461 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.3209. Min Act: -0.0000

Data Index: 890548 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.2807. Min Act: -0.0000

Data Index: 737983 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.2615. Min Act: -0.0000

Data Index: 655171 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.2896. Min Act: -0.0000

Data Index: 193379 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.4432. Min Range: -1.4432

Max Act: 1.2672. Min Act: -0.0000

Data Index: 1179822 (C4 (Web Text))

Max Activating Token Index: 960