Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1402 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1490. Min Act: -0.0003

Data Index: 455505 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1242. Min Act: -0.0004

Data Index: 494504 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1144. Min Act: -0.0003

Data Index: 978546 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1049. Min Act: -0.0003

Data Index: 423299 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1020. Min Act: -0.0004

Data Index: 1120307 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1053. Min Act: -0.0003

Data Index: 870176 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1034. Min Act: -0.0004

Data Index: 538423 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0993. Min Act: -0.0003

Data Index: 256314 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0983. Min Act: -0.0003

Data Index: 626391 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1009. Min Act: -0.0003

Data Index: 1180087 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0976. Min Act: -0.0003

Data Index: 1020021 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0982. Min Act: -0.0003

Data Index: 361212 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0961. Min Act: -0.0003

Data Index: 868509 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0960. Min Act: -0.0003

Data Index: 1253700 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1155823 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0946. Min Act: -0.0003

Data Index: 281279 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0956. Min Act: -0.0004

Data Index: 309771 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0933. Min Act: -0.0003

Data Index: 941229 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0969. Min Act: -0.0003

Data Index: 36796 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0930. Min Act: -0.0003

Data Index: 785340 (C4 (Web Text))

Max Activating Token Index: 537