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

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

Neuron 4396 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0003

Data Index: 181715 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0483. Min Act: -0.0003

Data Index: 583203 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0448. Min Act: -0.0002

Data Index: 77630 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0467. Min Act: -0.0003

Data Index: 398872 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1338213 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0457. Min Act: -0.0003

Data Index: 462615 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0456. Min Act: -0.0002

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0423. Min Act: -0.0003

Data Index: 683256 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0422. Min Act: -0.0002

Data Index: 44270 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0424. Min Act: -0.0003

Data Index: 31225 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0430. Min Act: -0.0003

Data Index: 403257 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0418. Min Act: -0.0003

Data Index: 226153 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1184101 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0416. Min Act: -0.0003

Data Index: 498250 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0400. Min Act: -0.0002

Data Index: 693698 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1163209 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0403. Min Act: -0.0003

Data Index: 613252 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0403. Min Act: -0.0002

Data Index: 916803 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0404. Min Act: -0.0002

Data Index: 142868 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0403. Min Act: -0.0003

Data Index: 860738 (C4 (Web Text))

Max Activating Token Index: 852