Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1927 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.3710. Min Act: -0.0001

Data Index: 517167 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.3212. Min Act: -0.0002

Data Index: 811049 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2790. Min Act: -0.0001

Data Index: 613618 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2336. Min Act: -0.0002

Data Index: 70373 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2489. Min Act: -0.0002

Data Index: 902325 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2572. Min Act: -0.0001

Data Index: 184345 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1668. Min Act: -0.0001

Data Index: 864892 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1309. Min Act: -0.0001

Data Index: 1167570 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2524. Min Act: -0.0002

Data Index: 710860 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1869. Min Act: -0.0001

Data Index: 991138 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0987. Min Act: -0.0001

Data Index: 22898 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0291. Min Act: -0.0001

Data Index: 620142 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1055. Min Act: -0.0001

Data Index: 1088433 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0161. Min Act: -0.0002

Data Index: 406448 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.9105. Min Act: -0.0001

Data Index: 19135 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1263284 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0545. Min Act: -0.0001

Data Index: 387835 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0103. Min Act: -0.0002

Data Index: 1063507 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0389. Min Act: -0.0002

Data Index: 251242 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.3710. Min Range: -1.3710

Max Act: 0.8888. Min Act: -0.0001

Data Index: 628418 (C4 (Web Text))

Max Activating Token Index: 816