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

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

Neuron 2448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.4139. Min Act: -0.0000

Data Index: 451760 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1141881 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3871. Min Act: -0.0000

Data Index: 184167 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3641. Min Act: -0.0000

Data Index: 917884 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3617. Min Act: -0.0000

Data Index: 421448 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3611. Min Act: -0.0000

Data Index: 421302 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3491. Min Act: -0.0000

Data Index: 655415 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1036372 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3356. Min Act: -0.0000

Data Index: 189861 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3310. Min Act: -0.0000

Data Index: 564828 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1141682 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3226. Min Act: -0.0000

Data Index: 961651 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3093. Min Act: -0.0000

Data Index: 220811 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3291. Min Act: -0.0000

Data Index: 821462 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3072. Min Act: -0.0000

Data Index: 694057 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3293. Min Act: -0.0000

Data Index: 442736 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3122. Min Act: -0.0000

Data Index: 451932 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1154523 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1153908 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.4139. Min Range: -0.4139

Max Act: 0.3029. Min Act: -0.0000

Data Index: 473509 (C4 (Web Text))

Max Activating Token Index: 478