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

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

Neuron 1997 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: 1.5793. Min Range: -1.5793

Max Act: 1.5793. Min Act: -0.0000

Data Index: 568267 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5601. Min Act: -0.0000

Data Index: 746924 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.5191. Min Act: -0.0000

Data Index: 557816 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1241575 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4213. Min Act: -0.0000

Data Index: 711312 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1168943 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.4746. Min Act: -0.0000

Data Index: 879537 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3722. Min Act: -0.0000

Data Index: 657113 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3460. Min Act: -0.0000

Data Index: 359460 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2700. Min Act: -0.0000

Data Index: 870340 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1081311 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1311420 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3214. Min Act: -0.0000

Data Index: 29394 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2865. Min Act: -0.0000

Data Index: 639477 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2727. Min Act: -0.0000

Data Index: 325243 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.3320. Min Act: -0.0000

Data Index: 339686 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.1975. Min Act: -0.0000

Data Index: 1269229 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.1884. Min Act: -0.0000

Data Index: 730361 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2495. Min Act: -0.0000

Data Index: 135228 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.5793. Min Range: -1.5793

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1290947 (C4 (Web Text))

Max Activating Token Index: 306