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

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

Neuron 3818 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2549. Min Act: -0.0000

Data Index: 916651 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0000

Data Index: 814204 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1030153 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1216251 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1963. Min Act: -0.0000

Data Index: 181328 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1214958 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2047. Min Act: -0.0000

Data Index: 439381 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1087278 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2246. Min Act: -0.0000

Data Index: 783570 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2016. Min Act: -0.0000

Data Index: 660438 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1994. Min Act: -0.0001

Data Index: 194303 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2137. Min Act: -0.0000

Data Index: 470125 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2217. Min Act: -0.0001

Data Index: 283851 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1997. Min Act: -0.0000

Data Index: 21124 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1977. Min Act: -0.0000

Data Index: 62949 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1987. Min Act: -0.0000

Data Index: 343142 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2115. Min Act: -0.0000

Data Index: 981962 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2123. Min Act: -0.0000

Data Index: 656718 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2040. Min Act: -0.0000

Data Index: 733820 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2175. Min Act: -0.0000

Data Index: 253135 (C4 (Web Text))

Max Activating Token Index: 390