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

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

Neuron 1600 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2163. Min Act: -0.0000

Data Index: 232016 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2132. Min Act: -0.0000

Data Index: 382647 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2156. Min Act: -0.0000

Data Index: 339544 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2016. Min Act: -0.0000

Data Index: 272801 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2030. Min Act: -0.0000

Data Index: 899180 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2059. Min Act: -0.0000

Data Index: 296331 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2061. Min Act: -0.0000

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1950. Min Act: -0.0000

Data Index: 25315 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1885. Min Act: -0.0000

Data Index: 932284 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2059. Min Act: -0.0000

Data Index: 924975 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2049. Min Act: -0.0000

Data Index: 750753 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.2135. Min Act: -0.0000

Data Index: 168568 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1960. Min Act: -0.0000

Data Index: 607299 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1970. Min Act: -0.0000

Data Index: 79053 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1067406 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1835. Min Act: -0.0000

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.2287. Min Range: -0.2287

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1152512 (C4 (Web Text))

Max Activating Token Index: 219